© 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. 125342
    Prev
    Next
    INDEX
    Explanations

    words and phrases

    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
    В
    0.56
    Ш
    0.56
    О
    0.53
    ро
    0.50
    Ви
    0.50
     образ
    0.49
     ото
    0.49
    Т
    0.49
    ке
    0.48
    τω
    0.47
    POSITIVE LOGITS
     golden
    0.56
     message
    0.50
     dance
    0.47
     shout
    0.47
     peeps
    0.46
     dancer
    0.46
     glass
    0.45
     people
    0.45
     antal
    0.44
    gewicht
    0.44
    Activations Density 0.001%

    No Known Activations