© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 94053
    Prev
    Next
    INDEX
    Explanations

    everyday release

    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
     වෙන
    0.58
    Parsed
    0.45
    vertret
    0.45
     Зо
    0.45
    volent
    0.44
    put
    0.43
    get
    0.43
    ת
    0.43
     de
    0.42
    ers
    0.42
    POSITIVE LOGITS
    |.
    0.50
    䒷
    0.46
     lamented
    0.45
    苺
    0.45
     Hickory
    0.45
     evocative
    0.44
     Canoe
    0.43
     Inject
    0.42
     mackerel
    0.42
     Floral
    0.42
    Activations Density 0.002%

    No Known Activations