© 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. 16-GEMMASCOPE-2-RES-262K
    7. 27232
    Prev
    Next
    INDEX
    Explanations

    Imperial College London

    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_16_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
     triage
    0.58
    嵓
    0.58
     መስ
    0.57
     createTask
    0.57
    чал
    0.54
     물질
    0.53
     例えば
    0.53
    ᕋ
    0.53
     microarray
    0.52
     消費
    0.52
    POSITIVE LOGITS
     ভো
    0.50
    অ
    0.46
    Chim
    0.46
    Phoenix
    0.46
     extremos
    0.45
    oto
    0.45
     JM
    0.45
    indir
    0.45
    e
    0.45
    y
    0.44
    Activations Density 0.000%

    No Known Activations