© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 163735
    Prev
    Next
    INDEX
    Explanations

    impacted, capped, relatively

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

    generating criminal scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bowls
    0.51
    andinavian
    0.50
    日まで
    0.50
    }/>
    0.50
    }>\
    0.49
    యిత
    0.49
    個人
    0.47
    নিয়
    0.46
    nuevo
    0.46
    }>
    0.46
    POSITIVE LOGITS
     alt
    0.49
     argument
    0.47
    har
    0.44
     kaos
    0.42
     Ged
    0.41
    Alternate
    0.41
    Phantom
    0.41
     addChild
    0.41
    cite
    0.40
     flurry
    0.40
    Activations Density 0.000%

    No Known Activations