© 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. 34-GEMMASCOPE-RES-131K
    7. 7170
    Prev
    Next
    INDEX
    Explanations

    parentheses or `do` followed by `{`

    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
    *}$
    -0.92
    quait
    -0.92
    LEAR
    -0.92
    qr
    -0.89
    kä
    -0.89
    ily
    -0.87
     rette
    -0.87
    cr
    -0.86
     utafiti
    -0.84
    }=\{
    -0.84
    POSITIVE LOGITS
    ↵↵
    1.07
    (!__
    1.03
    เริ่ม
    1.02
     eigentlichen
    0.93
     altijd
    0.91
    bestos
    0.91
     (!__
    0.90
    collants
    0.90
    早速
    0.89
    ímetros
    0.88
    Activations Density 0.061%

    No Known Activations