© 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. 190238
    Prev
    Next
    INDEX
    Explanations

    following links

    np_acts-logits-general · gemini-2.5-flash-lite

    structuring or defining specific entities

    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
    見た
    0.50
     aquí
    0.48
    ぼ
    0.48
    展现
    0.48
    嫁
    0.46
    ricamente
    0.45
    muestra
    0.45
    ᱩ
    0.45
    的可能性
    0.44
    これ
    0.44
    POSITIVE LOGITS
     string
    0.46
     greatest
    0.46
    following
    0.46
     following
    0.46
     followup
    0.46
     siguientes
    0.45
     Trip
    0.44
     tramp
    0.44
     nasled
    0.44
     args
    0.43
    Activations Density 0.000%

    No Known Activations