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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71673
    Prev
    Next
    INDEX
    Explanations

    chance to do

    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
    </h3>
    -2.05
    )$
    -1.70
     föränd
    -1.70
    俢
    -1.67
    the
    -1.67
     that
    -1.63
    }$
    -1.58
     ważne
    -1.57
     آوری
    -1.56
    {
    -1.56
    POSITIVE LOGITS
     to
    2.33
    轳
    1.83
     know
    1.82
    垆
    1.67
     նաև
    1.63
    大体
    1.62
    瘢
    1.62
    </b>
    1.55
     experim
    1.55
    However
    1.52
    Activations Density 0.009%

    No Known Activations