© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 161690
    Prev
    Next
    INDEX
    Explanations

    your question or enquiry

    np_acts-logits-general · gemini-2.5-flash-lite

    bypassing strong points or contamination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     கூறுக
    0.53
    л
    0.52
    сов
    0.47
     тоже
    0.47
    ק
    0.46
    ADO
    0.46
     पनि
    0.45
    ל
    0.45
    WK
    0.45
    Circles
    0.45
    POSITIVE LOGITS
     a
    0.51
     designated
    0.51
     assessed
    0.49
     evaluated
    0.48
     quadrant
    0.47
     evocative
    0.47
     achieved
    0.46
     intriguing
    0.44
     swallowing
    0.44
     performed
    0.44
    Activations Density 0.001%

    No Known Activations