© 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. 80335
    Prev
    Next
    INDEX
    Explanations

    book series, bonuses

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

    English translation of instructions

    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
    ної
    0.52
    ぐらい
    0.52
    ᆹ
    0.48
    ӑ
    0.48
    dv
    0.47
    ANG
    0.46
    ně
    0.46
    り
    0.46
    它
    0.46
    ون
    0.45
    POSITIVE LOGITS
     Coral
    0.46
     Initiation
    0.46
     Init
    0.45
     Wheeling
    0.45
     Local
    0.45
     Member
    0.44
     Representative
    0.44
     Ded
    0.44
     Courier
    0.44
     ক্রী
    0.44
    Activations Density 0.001%

    No Known Activations