© 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. 227267
    Prev
    Next
    INDEX
    Explanations

    skills to ensure

    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
    ᐟ
    0.55
     relaciona
    0.47
    explo
    0.46
     explotación
    0.46
    चारिक
    0.45
    inspect
    0.45
    texto
    0.43
     drawback
    0.43
    dihydroxy
    0.43
     reproducción
    0.42
    POSITIVE LOGITS
    Excess
    0.44
     мили
    0.43
     则
    0.43
     Newly
    0.43
    )`,
    0.43
    bod
    0.42
    Newly
    0.41
     फिर
    0.41
     tamu
    0.41
    Heat
    0.41
    Activations Density 0.001%

    No Known Activations