© 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. 87827
    Prev
    Next
    INDEX
    Explanations

    owner of recordPop under the grillIt provides an improvedHigh Reward

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

    program listings and definitions

    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
    angkat
    0.50
    㓈
    0.48
     বর্ণনা
    0.47
    enti
    0.47
    cepción
    0.46
    rants
    0.46
     முதலில்
    0.46
    单击
    0.46
    ⚫
    0.46
    angers
    0.45
    POSITIVE LOGITS
     legislator
    0.49
     lawmaker
    0.47
    겹
    0.44
     히
    0.44
     birdie
    0.44
    Expo
    0.42
     protocol
    0.41
    зера
    0.41
    *
    0.41
     move
    0.41
    Activations Density 0.000%

    No Known Activations