© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112026
    Prev
    Next
    INDEX
    Explanations

    societal breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    深
    0.46
     sock
    0.43
     tìm
    0.42
     raid
    0.42
     manifi
    0.41
     DON
    0.41
    <0x80>
    0.40
    员
    0.40
    垷
    0.40
     pod
    0.39
    POSITIVE LOGITS
    punctuation
    0.52
    machines
    0.51
     approximations
    0.47
    transitions
    0.45
     unfounded
    0.44
    থাক
    0.44
    ି
    0.44
    mere
    0.44
    ститут
    0.43
     церкви
    0.43
    Activations Density 0.000%

    No Known Activations