© 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. 197112
    Prev
    Next
    INDEX
    Explanations

    institutionalisation and decline

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

    data row or observation

    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
    autista
    0.49
    ovington
    0.49
     قی
    0.46
    otherwise
    0.44
    AUTHOR
    0.44
    Û
    0.44
    UM
    0.44
    NotIn
    0.43
    Ec
    0.43
     ܗܘ
    0.42
    POSITIVE LOGITS
    每一
    0.48
    先
    0.47
     speculating
    0.47
    லோ
    0.46
    紋
    0.45
    প্তাহ
    0.45
    不够
    0.45
    療
    0.45
     deletions
    0.45
    两
    0.45
    Activations Density 0.001%

    No Known Activations