© 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. 40-GEMMASCOPE-2-RES-262K
    7. 9610
    Prev
    Next
    INDEX
    Explanations

    SvelteKit Cloudflare code

    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_40_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
     Hallmark
    0.42
     Divide
    0.37
     sustain
    0.37
     Andrea
    0.36
    _{*}
    0.36
     dilute
    0.35
     Ex
    0.35
    (:,:,
    0.35
     Sampson
    0.35
     Samp
    0.35
    POSITIVE LOGITS
    workers
    0.38
    nity
    0.38
    omio
    0.37
    ліз
    0.36
    OX
    0.36
    Chemistry
    0.36
    loir
    0.36
    oluene
    0.36
    chloride
    0.35
    czę
    0.35
    Activations Density 0.002%

    No Known Activations