© 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. 3791
    Prev
    Next
    INDEX
    Explanations

    for our calculations

    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
     १३
    0.41
     технологии
    0.38
    🏛
    0.38
    sterreich
    0.38
     паліты
    0.38
    Checked
    0.38
     यूरोपीय
    0.38
     교통
    0.38
     అమ్మ
    0.37
    투
    0.37
    POSITIVE LOGITS
     kissing
    0.48
     swoją
    0.46
     making
    0.45
     membuat
    0.44
     replacing
    0.44
     apakah
    0.43
     haciendo
    0.41
     creating
    0.40
     onscreen
    0.40
     guna
    0.40
    Activations Density 0.004%

    No Known Activations