© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90863
    Prev
    Next
    INDEX
    Explanations

    code, citations, and between

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    пала
    -0.95
    crombie
    -0.87
    ?')
    -0.84
    ("")]
    -0.80
    /")
    -0.79
     alſo
    -0.78
    ڏ
    -0.78
    が
    -0.76
    ?=
    -0.75
    bildet
    -0.75
    POSITIVE LOGITS
    timacy
    0.87
    between
    0.87
    Į
    0.85
     nadie
    0.85
     Between
    0.85
    habitants
    0.82
    这几
    0.82
    Between
    0.81
    empt
    0.81
    NaN
    0.81
    Activations Density 0.006%

    No Known Activations