© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 13701
    Prev
    Next
    INDEX
    Explanations

    methodology and data in research

    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_65k_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
     aisément
    0.40
    ėtų
    0.40
    Assert
    0.40
    cellulose
    0.38
    榻
    0.37
    ামুটি
    0.36
    ید
    0.36
    绰
    0.36
     grainy
    0.35
     Sekunden
    0.35
    POSITIVE LOGITS
     habl
    0.35
     interviewing
    0.34
     yaitu
    0.34
     purchases
    0.34
     Moving
    0.34
     digunakan
    0.33
     dilaksanakan
    0.33
     Vaccines
    0.33
    <unused2152>
    0.33
     وتن
    0.32
    Activations Density 0.006%

    No Known Activations