© 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. 34-GEMMASCOPE-RES-131K
    7. 106795
    Prev
    Next
    INDEX
    Explanations

    after following nouns

    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_34/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
    .
    -3.23
    ).
    -3.02
    }$.
    -2.84
    。
    -2.56
    ។
    -2.41
    '].
    -2.33
    .
    -2.27
    ().
    -2.20
    %.
    -2.19
     ہے۔
    -2.09
    POSITIVE LOGITS
     to
    2.38
     ہے
    1.83
     but
    1.70
    かもしれませんが
    1.69
    了些
    1.65
    掾
    1.63
    abriel
    1.61
     offizi
    1.59
    acier
    1.59
    guigu
    1.58
    Activations Density 0.404%

    No Known Activations