© 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. 8952
    Prev
    Next
    INDEX
    Explanations

    creating pseudo code

    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
    ০
    1.47
    tired
    1.28
     अच्छे
    1.25
    cognitive
    1.20
    e
    1.19
    winner
    1.18
     এদিকে
    1.16
    
    1.14
    $),
    1.14
    ার
    1.12
    POSITIVE LOGITS
    ovat
    1.29
    ucky
    1.27
    icky
    1.26
     wann
    1.24
    чва
    1.24
    كي
    1.23
     autograph
    1.23
     circumst
    1.21
    ů
    1.19
    রের
    1.18
    Activations Density 0.000%

    No Known Activations