© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2743
    Prev
    Next
    INDEX
    Explanations

    filter pass bandwidth

    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
    utschen
    -0.74
    katkan
    -0.72
    푉
    -0.71
     sottile
    -0.70
    Cours
    -0.70
     poderá
    -0.69
    ρυσ
    -0.69
    荸
    -0.69
    ⮑
    -0.69
    *;
    -0.68
    POSITIVE LOGITS
    pass
    2.11
     pass
    2.08
     filter
    1.86
     Pass
    1.85
    Pass
    1.84
     filters
    1.83
    filter
    1.68
     filtering
    1.65
     Filter
    1.57
     passa
    1.55
    Activations Density 0.034%

    No Known Activations