© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129518
    Prev
    Next
    INDEX
    Explanations

    found in lists

    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
     because
    -2.92
     and
    -2.48
    ."
    -2.11
     it
    -2.00
     or
    -1.96
     at
    -1.93
     seems
    -1.92
     an
    -1.91
     any
    -1.91
     some
    -1.84
    POSITIVE LOGITS
    玊
    1.98
    sometimes
    1.89
     gemessen
    1.85
     wszystkich
    1.84
    often
    1.83
    slightly
    1.78
     dando
    1.75
    ఽ
    1.74
    reggio
    1.71
    躄
    1.71
    Activations Density 0.243%

    No Known Activations