© 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. 34-GEMMASCOPE-RES-131K
    7. 31972
    Prev
    Next
    INDEX
    Explanations

    number x number dimensions

    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
     related
    -0.92
     an
    -0.85
    があり
    -0.84
     from
    -0.83
    anatom
    -0.82
    </h1>
    -0.81
    y
    -0.79
    つける
    -0.79
    種類の
    -0.77
    避け
    -0.77
    POSITIVE LOGITS
     потом
    1.03
    aménagement
    0.93
    teurs
    0.92
     lipat
    0.92
    CEPT
    0.91
    ⇩
    0.91
     \"
    0.91
     gradi
    0.88
     säger
    0.87
    רושלים
    0.87
    Activations Density 0.024%

    No Known Activations