© 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. 22-GEMMASCOPE-2-RES-65K
    7. 7543
    Prev
    Next
    INDEX
    Explanations

    people find/report/experience

    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_22_width_65k_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
    嫻
    0.89
    ต่างๆ
    0.77
     باید
    0.77
    ರನ್ನು
    0.76
     counterparts
    0.75
    partners
    0.74
     были
    0.71
     deben
    0.71
    娴
    0.70
    mara
    0.70
    POSITIVE LOGITS
     sugest
    0.85
     argue
    0.82
    uggest
    0.77
    ススメ
    0.74
     siger
    0.74
     verwenden
    0.74
     argued
    0.74
     says
    0.74
     sih
    0.73
    forme
    0.73
    Activations Density 0.045%

    No Known Activations