© 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. 84422
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    『
    0.39
    編集
    0.39
    ágina
    0.39
    ága
    0.39
    ஆர்
    0.38
    usin
    0.38
    ísticas
    0.38
    钢
    0.38
    旳
    0.38
     steel
    0.37
    POSITIVE LOGITS
    rire
    0.44
     livelihood
    0.41
    leston
    0.40
     geen
    0.40
    ียบ
    0.38
     livelihoods
    0.38
     सक्सेस
    0.38
     indulging
    0.38
     nurtured
    0.37
     evident
    0.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.