© 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. 10-GEMMASCOPE-RES-131K
    7. 70363
    Prev
    Next
    INDEX
    Explanations

    removes the need to

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

    This neuron detects phrasing that highlights removing or eliminating a requirement—emphasizing convenience, simplification, or “no‐need” language.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     made
    -1.52
     from
    -1.51
     changed
    -1.45
     it
    -1.45
     changes
    -1.33
     at
    -1.32
     Mostly
    -1.31
     persön
    -1.31
     Somehow
    -1.30
     Apparently
    -1.29
    POSITIVE LOGITS
    ="
    1.71
    ＇
    1.54
     bús
    1.42
     mesures
    1.41
    镲
    1.40
    ılığı
    1.38
     domaines
    1.38
    镡
    1.37
    鹩
    1.37
     rekon
    1.35
    Activations Density 0.075%

    No Known Activations