© 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. 28178
    Prev
    Next
    INDEX
    Explanations

    stage, microphone, device, screen

    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
    r
    0.54
    tin
    0.54
    se
    0.51
    a
    0.47
    น
    0.46
    of
    0.45
    n
    0.45
    in
    0.45
    q
    0.45
    us
    0.44
    POSITIVE LOGITS
     waarop
    0.69
    fläche
    0.60
     grills
    0.57
    ওয়ার
    0.55
     TIME
    0.53
     umíst
    0.53
     slats
    0.52
    椅
    0.52
    上的
    0.51
     occupied
    0.51
    Activations Density 0.072%

    No Known Activations