© 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. 258089
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ysz
    0.47
    .
    0.45
    š
    0.45
    es
    0.44
    ada
    0.44
    unction
    0.43
     additions
    0.43
    an
    0.42
    StripMenuItem
    0.42
    kates
    0.42
    POSITIVE LOGITS
     Prensa
    0.46
     chcia
    0.46
    箓
    0.44
     organizacji
    0.44
     treści
    0.44
     potrzeb
    0.43
     واپسی
    0.42
     Maxine
    0.40
    蚓
    0.40
     buoyancy
    0.40
    Activations Density 0.003%

    No Known Activations