© 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. 19187
    Prev
    Next
    INDEX
    Explanations

    close to, destroyed by, located, game

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

    square root calculation

    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
    介绍了
    0.44
     Finger
    0.43
     člán
    0.42
     logiciels
    0.41
    Cock
    0.40
    Proble
    0.40
     Britannica
    0.38
    ฀
    0.38
     Scanner
    0.38
    Software
    0.37
    POSITIVE LOGITS
    IFUL
    0.49
    dwm
    0.46
     wynosi
    0.45
     accompl
    0.44
     resmi
    0.44
    offsetLeft
    0.44
    frow
    0.44
     संग्रहीत
    0.43
    iul
    0.42
    ૩
    0.42
    Activations Density 0.000%

    No Known Activations