© 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. 11251
    Prev
    Next
    INDEX
    Explanations

    payload usable tropes unique market

    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
    न
    2.76
    soever
    2.67
    sburg
    2.31
    istance
    2.28
    %%%%%%%%%%%%%%%%
    2.26
     equilibrio
    2.23
     तरफ
    2.20
    voll
    2.18
     entrare
    2.14
    ប្រទេស
    2.13
    POSITIVE LOGITS
    ح
    2.77
    it
    2.70
    ers
    2.67
    ்
    2.46
    ant
    2.45
    al
    2.34
    는
    2.31
    ert
    2.21
    ead
    2.13
    and
    2.08
    Activations Density 0.000%

    No Known Activations