© 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. 1147
    Prev
    Next
    INDEX
    Explanations

    acceptance and tolerance

    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
     angla
    1.33
    다
    1.28
    stellt
    1.26
     ruthenium
    1.24
     Му
    1.21
    sentences
    1.21
    tle
    1.21
     plunger
    1.20
    ylamine
    1.20
    Ş
    1.20
    POSITIVE LOGITS
    aday
    1.20
    ባቢ
    1.12
     refreshment
    1.11
     brush
    1.06
    ીર
    1.06
     forno
    1.05
    Responder
    1.05
     familiarity
    1.05
     st
    1.03
     Ferris
    1.03
    Activations Density 0.000%

    No Known Activations