© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66289
    Prev
    Next
    INDEX
    Explanations

    Fish poisoning news headlines

    np_acts-logits-general · gemini-2.5-flash-lite

    closing curly braces in programming code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects sequences of leading whitespace (indentation) in code or markup.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -1.00
     as
    -0.96
     various
    -0.90
     especially
    -0.88
     other
    -0.87
     during
    -0.86
     from
    -0.85
     virtually
    -0.81
     plus
    -0.81
     no
    -0.81
    POSITIVE LOGITS
    veranstaltungen
    1.02
    "}
    0.91
    ()}
    0.90
     geblieben
    0.90
    ?}
    0.90
     paulo
    0.87
    ();}
    0.87
    !]
    0.87
     расши
    0.85
    ęg
    0.81
    Activations Density 0.002%

    No Known Activations