© 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. 11503
    Prev
    Next
    INDEX
    Explanations

    officially marked events

    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
    ва
    2.14
    ts
    2.09
    которые
    1.98
    ヂストン
    1.89
    mehr
    1.89
    かの
    1.86
    rous
    1.85
    )}(\
    1.84
    テンツ
    1.80
    ده
    1.80
    POSITIVE LOGITS
    y
    2.94
    ر
    2.34
    el
    2.25
    ement
    2.18
    finn
    2.17
    ஸ்
    2.15
     tuổi
    2.14
    inating
    2.13
     repentance
    2.12
     regrett
    2.10
    Activations Density 0.007%

    No Known Activations