© 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. 84752
    Prev
    Next
    INDEX
    Explanations

    Mediterranean Sea

    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
    Evaluation
    0.50
    디
    0.47
    l
    0.46
    ec
    0.44
    يع
    0.44
    afs
    0.43
    に
    0.43
    Cr
    0.43
    expiration
    0.42
    Resolution
    0.42
    POSITIVE LOGITS
     streamer
    0.50
     teaser
    0.45
     commentator
    0.45
     signalled
    0.45
     legenda
    0.45
     gameState
    0.43
     alang
    0.43
     sceptical
    0.43
     neurotrans
    0.43
     lemongrass
    0.43
    Activations Density 0.000%

    No Known Activations