© 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. 49940
    Prev
    Next
    INDEX
    Explanations

    credit for, lucky enough, head implant

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

    structural elements

    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
    M
    0.51
    but
    0.46
    reserv
    0.46
    the
    0.44
     but
    0.43
    했지만
    0.43
     its
    0.43
     يؤ
    0.42
     eher
    0.42
     lakini
    0.42
    POSITIVE LOGITS
    开设
    0.49
     этих
    0.47
     जेव्हा
    0.46
    妓
    0.44
    🏘
    0.43
     цих
    0.43
     разных
    0.43
     drivetrain
    0.43
    вість
    0.42
     Typing
    0.42
    Activations Density 0.001%

    No Known Activations