© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47112
    Prev
    Next
    INDEX
    Explanations

    Fantasy genre

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﻳ
    0.47
    gående
    0.44
     تقسيم
    0.44
    agnie
    0.43
    vodu
    0.43
     puch
    0.43
    ultimate
    0.43
    encji
    0.43
     υψη
    0.43
     DTC
    0.42
    POSITIVE LOGITS
    {
    0.46
    ABEL
    0.46
    া
    0.45
    击
    0.45
    <0xAC>
    0.44
     französischen
    0.44
    లుగు
    0.44
     খা
    0.44
     rãi
    0.44
     Jahrhunderts
    0.43
    Activations Density 0.005%

    No Known Activations