© 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. 143399
    Prev
    Next
    INDEX
    Explanations

    quotations buffet painting feel clean

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

    governmental objectives or allows actions

    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
     returning
    0.52
     safeguards
    0.50
    ↵↵↵
    0.48
     accrued
    0.47
     newdata
    0.46
     indic
    0.46
     reass
    0.45
     mismanagement
    0.45
     nullable
    0.45
     pointer
    0.44
    POSITIVE LOGITS
    Collaboration
    0.67
     Collaboration
    0.64
     Zam
    0.63
    䨪
    0.52
     Subs
    0.52
    عي
    0.50
     Zwei
    0.49
    झा
    0.49
    ந்து
    0.48
    тування
    0.48
    Activations Density 0.000%

    No Known Activations