© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104391
    Prev
    Next
    INDEX
    Explanations

    quantifiable attributes and specifications

    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
    })).
    -0.99
     children
    -0.97
     uovo
    -0.94
     divisão
    -0.93
     energías
    -0.92
     appuntamento
    -0.92
     dieci
    -0.91
     violent
    -0.91
     soltanto
    -0.90
    ’).
    -0.90
    POSITIVE LOGITS
     in
    1.64
     (
    1.47
     at
    1.15
     trygg
    0.98
     lenguaje
    0.98
    力は
    0.98
    着头
    0.94
    不下
    0.94
     from
    0.94
    extAlignment
    0.91
    Activations Density 0.024%

    No Known Activations