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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72648
    Prev
    Next
    INDEX
    Explanations

    sinful life, perish, catchy tune

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

    The neuron fires on tokens containing the substring “sin,” i.e. words like “sinful,” “sinned,” etc.

    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
    </h4>
    -2.66
    튿
    -2.56
    廡
    -2.38
    bản
    -2.36
    鉕
    -2.36
     jednej
    -2.30
     rheinland
    -2.25
     giocatore
    -2.25
    赑
    -2.25
    橚
    -2.23
    POSITIVE LOGITS
    man
    2.28
    </i>
    2.19
    er
    2.17
    ↵↵
    2.13
    le
    2.13
    .
    2.08
     döv
    2.06
    F
    2.06
    ),
    2.06
    ity
    2.06
    Activations Density 0.002%

    No Known Activations