© 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. 222673
    Prev
    Next
    INDEX
    Explanations

    call, cut, adds

    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
    รส
    0.39
    jsoup
    0.38
    Milwaukee
    0.37
    💯
    0.36
     familiale
    0.36
     što
    0.36
     সড়
    0.36
     বক্তব
    0.36
     λόγω
    0.36
    쁩
    0.36
    POSITIVE LOGITS
    Call
    0.48
    call
    0.48
     call
    0.45
     Call
    0.42
    Cut
    0.39
     заключа
    0.38
     Cut
    0.38
    コール
    0.37
    CALL
    0.37
    serialization
    0.36
    Activations Density 0.000%

    No Known Activations