© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 125252
    Prev
    Next
    INDEX
    Explanations

    Lime, bitumen, business

    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_31_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
    د
    0.56
    д
    0.50
    درا
    0.41
    с
    0.41
    ဤ
    0.40
    aš
    0.39
    دون
    0.38
    čiau
    0.38
    emplate
    0.38
    دين
    0.37
    POSITIVE LOGITS
    SECONDARY
    0.52
    তুন
    0.50
    幄
    0.48
    airplane
    0.48
     salute
    0.47
     facade
    0.47
     инициа
    0.46
     rectMode
    0.46
     solenoid
    0.46
     stanow
    0.46
    Activations Density 0.000%

    No Known Activations