© 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. 191928
    Prev
    Next
    INDEX
    Explanations

    family, own, cleanliness

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

    leads to issues

    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
     Gesetz
    0.53
     판
    0.51
     einzel
    0.51
     알파
    0.49
    azen
    0.48
    insky
    0.47
    inska
    0.47
     జన్
    0.47
     القض
    0.46
    蠶
    0.46
    POSITIVE LOGITS
     photographing
    0.52
     Huntington
    0.49
     satisfying
    0.49
     photograph
    0.49
     pertinente
    0.49
     stray
    0.47
     camouflage
    0.47
     Fujifilm
    0.46
    работки
    0.46
     measuring
    0.45
    Activations Density 0.001%

    No Known Activations