© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 20017
    Prev
    Next
    INDEX
    Explanations

    announces/reports/releases news or results

    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
    ังหวัด
    0.47
    entor
    0.46
    ofy
    0.46
    prom
    0.45
    तपुर
    0.45
    avu
    0.44
    ע
    0.44
    п
    0.43
    bella
    0.43
    angels
    0.43
    POSITIVE LOGITS
     fat
    0.46
     cheap
    0.44
     cheapest
    0.42
     Cheap
    0.42
     cheese
    0.42
     meat
    0.42
     manche
    0.41
     are
    0.41
     Official
    0.41
     gastronomic
    0.41
    Activations Density 0.000%

    No Known Activations