© 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. 11955
    Prev
    Next
    INDEX
    Explanations

    section headers or lists

    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
    ic
    1.48
    ి
    1.46
    ि
    1.32
    ி
    1.30
    i
    1.27
    सी
    1.24
    as
    1.21
    ো
    1.19
    and
    1.18
    وا
    1.17
    POSITIVE LOGITS
     экране
    1.31
    ности
    1.31
     $[\
    1.28
    чена
    1.25
    𝐥
    1.23
    ங்கிணை
    1.22
    शेद
    1.21
    
    1.20
     состоянии
    1.20
    tte
    1.16
    Activations Density 0.122%

    No Known Activations