© 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. 12107
    Prev
    Next
    INDEX
    Explanations

    how to use it

    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
     springboard
    1.32
     pobl
    1.31
     варто
    1.24
     ஆ
    1.23
    RENCE
    1.23
    ീസ്
    1.22
    <0x80>
    1.19
     طی
    1.17
     būt
    1.17
    ため
    1.16
    POSITIVE LOGITS
    ate
    1.30
    confident
    1.20
    us
    1.15
    ër
    1.14
    虎
    1.09
    ্যান
    1.06
     regret
    1.05
    iramente
    1.05
    यों
    1.03
    Ñ
    1.03
    Activations Density 0.031%

    No Known Activations