© 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. 31-GEMMASCOPE-2-RES-262K
    7. 26054
    Prev
    Next
    INDEX
    Explanations

    even, especially, sometimes

    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
    ীক
    0.39
    Step
    0.38
    つまり
    0.38
    Ἑ
    0.38
    plated
    0.37
    basically
    0.37
    decision
    0.37
    ABCD
    0.37
    step
    0.36
    POINT
    0.36
    POSITIVE LOGITS
     nawet
    0.50
     иногда
    0.49
     навіть
    0.46
     🥰
    0.43
     even
    0.42
     Bahkan
    0.42
     найбіль
    0.41
    собенно
    0.41
     даже
    0.40
     incluso
    0.39
    Activations Density 0.080%

    No Known Activations