© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 305
    Prev
    Next
    INDEX
    Explanations

    database keywords and commands

    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_29_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
     ⚫
    0.94
    ഋ
    0.92
     drenched
    0.88
     gewonnen
    0.86
     Implant
    0.85
     dihad
    0.84
     حجت
    0.83
    abhuto
    0.83
     Caedwalla
    0.83
    _{*}(
    0.83
    POSITIVE LOGITS
     FROM
    1.70
     WHERE
    1.65
     ON
    1.52
    FROM
    1.47
     INTO
    1.44
     WITH
    1.42
    WHERE
    1.41
     IN
    1.39
     OF
    1.36
     AS
    1.36
    Activations Density 0.380%

    No Known Activations