© 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. 5403
    Prev
    Next
    INDEX
    Explanations

    pump of

    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
    El
    0.49
    the
    0.48
    Es
    0.47
    Pot
    0.46
    Jefferson
    0.46
    Ms
    0.45
    ង
    0.43
    甲
    0.43
    山
    0.43
    Ма
    0.43
    POSITIVE LOGITS
     เป้า
    0.46
     معناها
    0.44
    줍니다
    0.43
     whirl
    0.43
     condesc
    0.43
     commence
    0.42
     महिले
    0.41
    চ্চার
    0.41
     guill
    0.40
     />}
    0.39
    Activations Density 0.000%

    No Known Activations