© 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. 41231
    Prev
    Next
    INDEX
    Explanations

    areas, aspects, rules

    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
    পাই
    0.49
    멀
    0.47
    
    0.45
     coseno
    0.45
    Methylsulfanyl
    0.45
    愔
    0.44
    িল্ল
    0.44
     অঙ্
    0.44
    كنولوج
    0.44
    ரள
    0.44
    POSITIVE LOGITS
     (
    0.55
    v
    0.55
     ([
    0.54
    .
    0.54
     -
    0.50
     v
    0.49
     necessitate
    0.47
     aka
    0.46
     )
    0.46
    ".
    0.43
    Activations Density 0.001%

    No Known Activations