© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 4033
    Prev
    Next
    INDEX
    Explanations

    specific terms and separators

    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_17_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
     какое
    0.71
    窰
    0.71
     каких
    0.71
     कहाँ
    0.70
    деги
    0.70
    osphate
    0.68
     sizin
    0.68
    のお店
    0.67
     विवाद
    0.67
     માહિતી
    0.66
    POSITIVE LOGITS
    ;
    1.20
     ;
    1.15
    ;
    1.09
     oraz
    1.04
    *;
    1.03
     AND
    1.02
    $;
    1.01
     तथा
    0.98
     және
    0.97
    .;
    0.96
    Activations Density 0.336%

    No Known Activations