© 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. 60229
    Prev
    Next
    INDEX
    Explanations

    specific token followed by colon or phrase

    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
    según
    -1.01
    Hapana
    -0.94
    hygiène
    -0.92
    polished
    -0.91
    に於
    -0.89
    𖤐
    -0.88
     bertujuan
    -0.88
    外国人
    -0.87
    ҫ
    -0.87
    sólo
    -0.87
    POSITIVE LOGITS
    หม
    0.94
    であり
    0.92
     interventions
    0.90
    quered
    0.88
     qualitatively
    0.84
    nyc
    0.82
     swim
    0.81
     работ
    0.81
     Interventions
    0.80
    čiť
    0.80
    Activations Density 0.014%

    No Known Activations