© 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. 22-GEMMASCOPE-RES-131K
    7. 33140
    Prev
    Next
    INDEX
    Explanations

    requirement or obligation

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

    The neuron fires on occurrences of the word “must,” highlighting requirement or obligation statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    葙
    -2.23
    牁
    -2.19
    蹰
    -2.16
    ዌ
    -2.03
    ⃢
    -2.03
     graciosos
    -2.02
     triomphe
    -2.02
    ências
    -2.02
     vorigen
    -2.02
    ⧠
    -1.95
    POSITIVE LOGITS
     be
    2.91
    s
    2.42
     also
    2.05
    м
    2.05
    I
    2.02
    т
    1.95
    i
    1.94
     电影
    1.91
    <i>
    1.87
    <strong>
    1.84
    Activations Density 0.022%

    No Known Activations