© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 210388
    Prev
    Next
    INDEX
    Explanations

    David followed by surname or initial

    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
    //*
    0.42
    प्ताहिक
    0.41
     cognitiva
    0.40
     vacío
    0.36
    citenamefont
    0.36
    ='{{
    0.36
    恂
    0.35
     내부
    0.35
     muere
    0.35
    IfNeeded
    0.35
    POSITIVE LOGITS
    ່ນ
    0.40
    阊
    0.40
     Sko
    0.40
     ske
    0.39
     Scol
    0.39
     अग्नि
    0.38
    众
    0.38
     iniz
    0.38
    众多
    0.37
     ex
    0.37
    Activations Density 0.001%

    No Known Activations