© 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. 136092
    Prev
    Next
    INDEX
    Explanations

    container along, Edge is, back along

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

    characters or what

    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
    ︹
    0.54
    เฉ
    0.51
    되
    0.49
    itectura
    0.48
    새
    0.48
    į
    0.47
    λυ
    0.46
    সং
    0.46
    فاعل
    0.45
    룽
    0.45
    POSITIVE LOGITS
     ISD
    0.54
     ホワイト
    0.53
    comstock
    0.50
     Silva
    0.49
    hazard
    0.48
    kr
    0.48
     MSRP
    0.46
    pV
    0.46
     hazard
    0.46
    也要
    0.46
    Activations Density 0.000%

    No Known Activations