© 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. 4160
    Prev
    Next
    INDEX
    Explanations

    Res, AccountId, Bei, Ai

    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
     int
    0.47
     එක
    0.44
     venting
    0.41
     ප
    0.41
     หรือ
    0.41
    ʃ
    0.40
     YAML
    0.39
    ""
    0.39
    ณิต
    0.39
     進
    0.39
    POSITIVE LOGITS
    Julian
    0.43
    Rés
    0.42
     डाली
    0.41
    ecto
    0.41
    ាត់
    0.40
    AccountId
    0.39
     circulation
    0.39
    Bei
    0.39
    Residence
    0.39
    Ai
    0.38
    Activations Density 0.000%

    No Known Activations