© 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. 13699
    Prev
    Next
    INDEX
    Explanations

    country, world, globally, platform, frameworks

    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
     apparition
    0.46
    á
    0.44
    />}/>
    0.43
     appré
    0.41
     scène
    0.41
     stabbing
    0.41
     stab
    0.41
     wouldn
    0.41
    ítható
    0.41
     sécrétion
    0.41
    POSITIVE LOGITS
    MEM
    0.42
     (
    0.39
     (‘
    0.39
    Supplementary
    0.38
    Ju
    0.38
     aks
    0.38
     Balloon
    0.37
    stimulating
    0.37
     要
    0.37
    forming
    0.37
    Activations Density 0.000%

    No Known Activations