© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24507
    Prev
    Next
    INDEX
    Explanations

    temperature, disease, ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     روم
    0.48
    comando
    0.44
    ջ
    0.43
     swivel
    0.42
     protested
    0.41
     loophole
    0.41
    וד
    0.41
     uproar
    0.41
    ק
    0.41
     grud
    0.41
    POSITIVE LOGITS
    )$.
    0.52
    দীন
    0.44
    ℃
    0.44
     zodat
    0.43
     Eating
    0.43
     Sewage
    0.42
     Heating
    0.41
     Testing
    0.41
     Temperatures
    0.41
     ).
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.