© 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. 206283
    Prev
    Next
    INDEX
    Explanations

    during the 120-day period

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

    He initially believed

    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
    :
    0.59
     ذ
    0.45
    +:
    0.43
    itano
    0.43
     well
    0.42
     मिनट
    0.42
     хорошо
    0.42
     Significance
    0.42
    Bomb
    0.41
    氵
    0.41
    POSITIVE LOGITS
    к
    0.58
     grayish
    0.57
     bureaucr
    0.52
     interacted
    0.52
    ம
    0.52
     acabó
    0.51
     wrinkles
    0.47
     algebras
    0.47
     Làm
    0.47
    𝚕
    0.46
    Activations Density 0.002%

    No Known Activations