© 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. 243439
    Prev
    Next
    INDEX
    Explanations

    foreign names of places objects or concepts

    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
    ptitle
    0.64
    staking
    0.53
    بي
    0.52
    𝖽
    0.52
    𝘸
    0.49
    ty
    0.48
     주요
    0.48
    ts
    0.47
    twitter
    0.47
    特别
    0.47
    POSITIVE LOGITS
     barrio
    0.49
     cathedral
    0.49
     Г
    0.48
     vetro
    0.48
     conical
    0.48
     caldera
    0.47
     naï
    0.46
     coefficient
    0.46
     inspector
    0.46
     step
    0.46
    Activations Density 0.000%

    No Known Activations