© 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. 111341
    Prev
    Next
    INDEX
    Explanations

    when a clue

    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
     वायू
    0.46
    acité
    0.45
    ²
    0.45
    ayutt
    0.44
     измерения
    0.44
    avaient
    0.44
    甴
    0.43
    écriture
    0.42
     γιατί
    0.41
    ⁷
    0.41
    POSITIVE LOGITS
     Matthew
    0.45
     says
    0.43
     Chief
    0.43
     Surgeons
    0.43
     Cleveland
    0.42
     Judges
    0.42
     Hose
    0.42
     Coolidge
    0.42
     осуществления
    0.42
     Receiver
    0.41
    Activations Density 0.006%

    No Known Activations