© 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. 12824
    Prev
    Next
    INDEX
    Explanations

    slide titles and descriptions

    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
    OPHY
    0.45
    气
    0.40
    あなたが
    0.40
     buoyancy
    0.39
     आपका
    0.39
     realidad
    0.38
     booths
    0.38
    钎
    0.38
    >;</
    0.38
     вашей
    0.38
    POSITIVE LOGITS
    etor
    0.36
    ational
    0.35
    ătă
    0.35
     Bryan
    0.34
    reviewer
    0.34
    ients
    0.33
     Dutchman
    0.33
    atac
    0.33
    actic
    0.32
    atical
    0.32
    Activations Density 0.000%

    No Known Activations