© 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. 21074
    Prev
    Next
    INDEX
    Explanations

    explaining why something works

    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
     כל
    0.40
    و
    0.39
    ו
    0.38
    ա
    0.36
    のス
    0.35
     and
    0.33
     всю
    0.33
     partea
    0.33
    ת
    0.33
    ﻛ
    0.33
    POSITIVE LOGITS
    বার্গ
    0.40
    ették
    0.33
    xSpeed
    0.32
     Nhiều
    0.32
    ických
    0.32
    čke
    0.32
     is
    0.31
    agge
    0.31
    abilă
    0.31
     Là
    0.31
    Activations Density 0.074%

    No Known Activations