© 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-262K
    7. 10994
    Prev
    Next
    INDEX
    Explanations

    com or org followed by /

    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_262k_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
    ti
    1.31
     eliminate
    1.31
    e
    1.25
     miRNAs
    1.22
    y
    1.18
     cerevisiae
    1.18
     leptons
    1.16
     replenished
    1.16
     reputations
    1.16
    ^*
    1.14
    POSITIVE LOGITS
    дні
    1.55
    ਰ
    1.33
     právě
    1.32
    ﮨ
    1.30
    étation
    1.27
    ਜ
    1.25
    ਿਕ
    1.24
    
    1.22
    ्या
    1.21
     ebenso
    1.20
    Activations Density 0.027%

    No Known Activations