© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9567
    Prev
    Next
    INDEX
    Explanations

    laws and imagery

    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
    ం
    5.31
    ം
    5.22
    ر
    4.59
    an
    4.52
    ان
    4.45
    ம்
    4.45
    o
    4.43
    ম
    3.96
    ه
    3.89
    ে
    3.89
    POSITIVE LOGITS
    ━━━━
    3.00
     jati
    2.77
    ﺱ
    2.75
    ٰ
    2.70
     monol
    2.67
     deu
    2.65
    ﻭ
    2.64
    ς
    2.53
     chances
    2.53
     instincts
    2.52
    Activations Density 0.083%

    No Known Activations