© 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. 66871
    Prev
    Next
    INDEX
    Explanations

    socially or morally disapproved actions

    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_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
     our
    -1.55
    ZH
    -1.30
    ONSORED
    -1.24
    tiembre
    -1.20
     katkıda
    -1.18
     omnes
    -1.17
     maceta
    -1.16
     disheart
    -1.16
    Wc
    -1.15
    紲
    -1.15
    POSITIVE LOGITS
     to
    1.53
     for
    1.25
    quely
    1.20
    botten
    1.13
    能不能
    1.13
     parlando
    1.13
    การ
    1.12
    richtungen
    1.09
     właśnie
    1.09
     compleanno
    1.09
    Activations Density 0.059%

    No Known Activations