© 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. 76637
    Prev
    Next
    INDEX
    Explanations

    age and description

    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
     tailings
    0.47
    Prairie
    0.45
    áu
    0.42
    υτό
    0.42
    ذ
    0.42
     প্রাই
    0.41
    ัย
    0.41
     vesicles
    0.40
     Archaeological
    0.40
    ynyl
    0.40
    POSITIVE LOGITS
    動き
    0.42
    动
    0.41
     испы
    0.41
     मरने
    0.41
     esetén
    0.40
     առաջ
    0.40
     solvable
    0.39
    }}$$
    0.39
     dexter
    0.39
     esetben
    0.39
    Activations Density 0.016%

    No Known Activations