© 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. 71474
    Prev
    Next
    INDEX
    Explanations

    development and stopping

    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
     nerve
    0.51
    ICHIGAN
    0.44
     handwriting
    0.43
     mammary
    0.43
     neurological
    0.42
    ُوْ
    0.42
    惀
    0.42
    कांच्या
    0.41
     Nerve
    0.41
    का
    0.41
    POSITIVE LOGITS
    t
    0.55
    ton
    0.48
    bak
    0.46
    inky
    0.45
    sk
    0.45
    tom
    0.45
    Murray
    0.45
    create
    0.44
    mates
    0.44
    tile
    0.44
    Activations Density 0.002%

    No Known Activations