© 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. 136157
    Prev
    Next
    INDEX
    Explanations

    questions about finances

    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
    Ти
    0.53
    ﻐ
    0.50
    др
    0.50
     електро
    0.47
    ಂಗ್
    0.47
     اوپر
    0.46
    స్తోంది
    0.46
    ОР
    0.46
    StatusCommand
    0.45
    ంగ్
    0.45
    POSITIVE LOGITS
     =
    0.42
     사건
    0.42
     găsit
    0.40
    yla
    0.40
    rier
    0.40
     nieuws
    0.39
    这
    0.39
    ella
    0.38
    {
    0.38
     nhựa
    0.38
    Activations Density 0.006%

    No Known Activations