© 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. 9715
    Prev
    Next
    INDEX
    Explanations

    expressing possibility with could

    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
    銕
    -2.19
    ㆆ
    -2.17
    ቍ
    -2.08
     炖
    -1.91
    ꦧ
    -1.88
    
    -1.88
    Spolja
    -1.84
    最后由
    -1.81
    癭
    -1.81
    〠
    -1.80
    POSITIVE LOGITS
     be
    3.36
    </em>
    2.58
    <em>
    2.47
    }{
    2.23
    ’
    2.20
    —
    2.17
    <
    2.13
     also
    2.08
    i
    2.06
    C
    2.03
    Activations Density 0.036%

    No Known Activations