© 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-16K
    7. 1127
    Prev
    Next
    INDEX
    Explanations

    🤪 emoji and numbers

    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_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
    en
    3.50
    ل
    3.15
    al
    3.10
    in
    2.98
    t
    2.97
    y
    2.96
    er
    2.85
    es
    2.84
    is
    2.82
    oretically
    2.82
    POSITIVE LOGITS
    0
    1.65
     लेकर
    1.56
    7
    1.53
    6
    1.50
    ༌
    1.49
     través
    1.48
    8
    1.47
    Е
    1.46
    ″
    1.41
    ^{*}
    1.40
    Activations Density 0.649%

    No Known Activations