© 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. 10-GEMMASCOPE-RES-131K
    7. 47819
    Prev
    Next
    INDEX
    Explanations

    cefn-parc, Puerto Rico, Petersen, Bodging, Guzman

    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_10/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
    (!__
    -1.84
     diversa
    -1.80
     illustrates
    -1.77
     was
    -1.69
    ")
    -1.64
    ");
    -1.63
    同様に
    -1.63
     To
    -1.58
     pronta
    -1.56
     avoids
    -1.55
    POSITIVE LOGITS
     serien
    1.90
     beton
    1.84
     uren
    1.77
    –
    1.76
     alkoh
    1.76
     stammen
    1.72
    “-
    1.69
     bluza
    1.68
    ’
    1.68
     blau
    1.65
    Activations Density 0.370%

    No Known Activations