© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4174
    Prev
    Next
    INDEX
    Explanations

    style or inspired by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_16k_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
     oriented
    0.50
     kinase
    0.48
    _
    0.48
     hydro
    0.47
     inter
    0.46
     homeostasis
    0.46
     arrays
    0.44
     tightly
    0.44
     multicellular
    0.43
     groups
    0.42
    POSITIVE LOGITS
     Wszyst
    0.54
     Courthouse
    0.54
     フランス
    0.53
    adayo
    0.52
    ಿ
    0.52
     Stakes
    0.50
     Refunds
    0.50
     Redeem
    0.50
    bitkan
    0.50
     みんな
    0.50
    Activations Density 0.000%

    No Known Activations