© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 343
    Prev
    Next
    INDEX
    Explanations

    early informational context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     янва
    0.82
    drawString
    0.78
    とのこと
    0.77
    ▪
    0.76
    🐹
    0.75
    😡
    0.73
     tari
    0.73
     filoz
    0.73
    (?)
    0.72
    呪
    0.72
    POSITIVE LOGITS
     nevertheless
    1.26
    褔
    1.16
     epidermis
    1.16
     comprehend
    1.16
     obtainable
    1.14
     healthful
    1.13
     distinctive
    1.13
     adore
    1.13
     sufferers
    1.12
     safegu
    1.11
    Activations Density 2.508%

    No Known Activations