© 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. 76843
    Prev
    Next
    INDEX
    Explanations

    potentially even

    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
    坌
    0.48
     时
    0.47
    ae
    0.44
    criptions
    0.44
    怛
    0.44
     Wakefield
    0.44
    同学
    0.44
    zył
    0.44
    岕
    0.43
    izzato
    0.43
    POSITIVE LOGITS
     extrapolate
    0.53
     acide
    0.49
     addirittura
    0.49
     ameryka
    0.48
     eski
    0.46
     spiral
    0.46
     additionally
    0.45
     export
    0.45
    アメリカ
    0.45
     nawet
    0.45
    Activations Density 0.005%

    No Known Activations