© 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. 108123
    Prev
    Next
    INDEX
    Explanations

    components, filters, and tags

    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
     samarbe
    0.54
     reunião
    0.47
     situação
    0.45
     bleibt
    0.44
    纶
    0.43
     verwendeten
    0.43
     Hearings
    0.43
     gebru
    0.42
    తోంది
    0.42
    денциа
    0.42
    POSITIVE LOGITS
    simply
    0.53
    ಹಾರ
    0.50
    頡
    0.48
    vaj
    0.48
    planetary
    0.47
    x
    0.47
    huang
    0.46
    r
    0.46
    w
    0.46
    batches
    0.44
    Activations Density 0.001%

    No Known Activations