© 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. 33470
    Prev
    Next
    INDEX
    Explanations

    factors and considerations

    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
     from
    -0.98
     for
    -0.95
     Even
    -0.88
     even
    -0.86
     with
    -0.80
    पी
    -0.78
     by
    -0.77
     or
    -0.76
     at
    -0.74
     choose
    -0.73
    POSITIVE LOGITS
     nature
    1.34
     factors
    1.22
    nature
    1.13
     history
    1.03
    Factors
    1.02
    Gravity
    1.00
    gravity
    1.00
    artigen
    0.98
     factor
    0.97
    ਯ
    0.96
    Activations Density 0.021%

    No Known Activations