© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27216
    Prev
    Next
    INDEX
    Explanations

    mom, kids, listening

    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_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
    )}$.
    -1.00
     />
    -0.98
    dotto
    -0.94
    }}{{
    -0.90
     Historie
    -0.90
    сите
    -0.86
    밖
    -0.85
     debates
    -0.84
    大家
    -0.84
    下拉
    -0.84
    POSITIVE LOGITS
     please
    1.61
     their
    1.20
     here
    1.16
     beware
    0.99
    themselves
    0.98
    以及
    0.98
    please
    0.97
     hereby
    0.93
    Their
    0.92
     rằng
    0.91
    Activations Density 0.028%

    No Known Activations