© 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. 128261
    Prev
    Next
    INDEX
    Explanations

    different coverage styles

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

    response to prompt or issue

    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
    veloppement
    0.50
     অন্যদিকে
    0.49
    א
    0.48
     electricidad
    0.48
    algèbre
    0.47
    enfance
    0.47
    erenza
    0.46
    az
    0.46
     conectar
    0.46
    ارا
    0.46
    POSITIVE LOGITS
     間
    0.51
     Sleeping
    0.46
     掛け
    0.44
     modernist
    0.44
     Rotten
    0.44
     Focused
    0.44
     Breaking
    0.44
     Ships
    0.43
     सुरू
    0.43
     กิน
    0.43
    Activations Density 0.000%

    No Known Activations