© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 167220
    Prev
    Next
    INDEX
    Explanations

    tips outlined

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    ¿
    0.48
     graphical
    0.41
     ¿
    0.39
     मद्देनजर
    0.39
    ได้รับการ
    0.39
     необходимость
    0.38
    zeugung
    0.38
     unin
    0.38
    graphic
    0.37
    תוך
    0.37
    POSITIVE LOGITS
    绢
    0.44
    যানী
    0.40
    欣
    0.39
     spots
    0.38
    стья
    0.37
    कारात्मक
    0.37
     Cairo
    0.36
     Osm
    0.36
    ържа
    0.36
     silverware
    0.35
    Activations Density 0.000%

    No Known Activations