© 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. 199436
    Prev
    Next
    INDEX
    Explanations

    good-value deals

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

    poised to be

    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
    㸮
    0.46
    गल
    0.43
     মনোনয়ন
    0.42
     ஈடுபட்ட
    0.42
    )।
    0.41
     मानवीय
    0.41
     beaver
    0.40
     Saur
    0.40
    癀
    0.40
    ås
    0.40
    POSITIVE LOGITS
     signatures
    0.55
     indispensable
    0.55
     occupants
    0.49
     imprim
    0.48
     membre
    0.48
     dissidents
    0.47
     formations
    0.46
     remnants
    0.46
     membro
    0.46
     placards
    0.46
    Activations Density 0.000%

    No Known Activations