© 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. 135008
    Prev
    Next
    INDEX
    Explanations

    location names and titles

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

    context and examples

    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
     if
    0.50
     }}
    0.49
    Stages
    0.46
    on
    0.46
     Prand
    0.45
    cis
    0.44
    Completion
    0.44
    Deadline
    0.43
     "));
    0.42
    it
    0.41
    POSITIVE LOGITS
     nonspecific
    0.58
    ENGTH
    0.50
    鳧
    0.49
     ಮಾಹಿತಿ
    0.48
    𝙴
    0.48
     ined
    0.47
    ujjati
    0.47
    Н
    0.47
     characterized
    0.46
     lacked
    0.45
    Activations Density 0.000%

    No Known Activations