© 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. 123340
    Prev
    Next
    INDEX
    Explanations

    sentence breaks

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

    lists of 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
     deaths
    0.46
     hardship
    0.45
    ून्य
    0.44
     Housing
    0.43
     Mutations
    0.43
     ग्रामीण
    0.42
     $("#
    0.42
     పరిస్థి
    0.42
     fatt
    0.41
     Thromb
    0.41
    POSITIVE LOGITS
     někol
    0.51
     profundamente
    0.44
    갠
    0.44
     tý
    0.43
    то
    0.42
    맘
    0.42
    🪐
    0.42
    仔细
    0.41
    粿
    0.41
    лось
    0.41
    Activations Density 0.000%

    No Known Activations