© 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. 11871
    Prev
    Next
    INDEX
    Explanations

    asking to chat about

    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
    er
    2.81
    a
    2.15
    es
    2.14
    ing
    2.11
    с
    2.04
    sn
    2.03
    manship
    2.03
    speed
    1.94
    ce
    1.93
    overs
    1.91
    POSITIVE LOGITS
    𝖔
    2.19
     tecnológicas
    2.09
     successively
    2.09
     tille
    2.01
     tens
    2.00
    etição
    1.99
    <unused1903>
    1.99
    राधिक
    1.96
     javafx
    1.96
     trabal
    1.90
    Activations Density 0.025%

    No Known Activations