© 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. 34-GEMMASCOPE-RES-131K
    4. 2244
    Prev
    Next
    INDEX
    Explanations

    names starting with Ș, Sh, or S

    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
     hydrat
    -0.80
     finis
    -0.79
    但却
    -0.77
    ницу
    -0.76
    fft
    -0.76
     bret
    -0.76
    कृति
    -0.76
    дол
    -0.75
     both
    -0.75
    lico
    -0.74
    POSITIVE LOGITS
     condiciones
    0.93
     conditions
    0.91
     умова
    0.88
     persönlich
    0.84
     protegido
    0.82
    条件
    0.81
    激烈
    0.80
     oculto
    0.78
     condizione
    0.76
     delicada
    0.76
    Activations Density 0.007%

    No Known Activations