© 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. 36504
    Prev
    Next
    INDEX
    Explanations

    model sailing ships

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

    kill, symptoms, shit, drug code words

    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
     c
    0.46
    0.46
    rb
    0.46
    в
    0.46
     ${\
    0.45
     ‘
    0.45
    rs
    0.45
     p
    0.45
     event
    0.45
     w
    0.43
    POSITIVE LOGITS
    깜
    0.51
    ሦ
    0.50
    䒠
    0.48
    を書
    0.47
    噻
    0.46
    handlung
    0.46
    雒
    0.46
     लंबाई
    0.46
    箅
    0.45
    ایط
    0.45
    Activations Density 0.000%

    No Known Activations