© 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. 184593
    Prev
    Next
    INDEX
    Explanations

    describing specific attributes or types

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

    indicates levels or components

    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
    া
    0.46
    ጽ
    0.45
    truth
    0.45
    )。
    0.44
    OSE
    0.43
    のと
    0.43
    い
    0.42
     ム
    0.42
    ）。
    0.41
     অনেকটাই
    0.41
    POSITIVE LOGITS
     nacionais
    0.51
     adultes
    0.51
     suddiv
    0.51
     aul
    0.51
     nación
    0.50
    բ
    0.50
     unskilled
    0.50
     dispoz
    0.50
     adulti
    0.50
     reten
    0.49
    Activations Density 0.000%

    No Known Activations