© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10914
    Prev
    Next
    INDEX
    Explanations

    positive things, times, and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    嵋
    0.85
    й
    0.84
    ה
    0.81
    요
    0.78
    a
    0.75
     fluid
    0.74
    ށް
    0.72
    isatie
    0.72
    ﻧ
    0.72
     clarity
    0.70
    POSITIVE LOGITS
    و
    1.03
    ফ
    0.98
     totalité
    0.95
    entire
    0.93
     amounting
    0.89
     primaire
    0.86
    必ず
    0.85
     сочи
    0.85
    ném
    0.85
    ie
    0.85
    Activations Density 0.080%

    No Known Activations