© 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. 172557
    Prev
    Next
    INDEX
    Explanations

    diagrams and teaching

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

    around , : * £

    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
     indebtedness
    0.50
     inefficiencies
    0.47
     ratios
    0.46
    온
    0.44
     factors
    0.44
     typos
    0.43
     monies
    0.43
    ইংরেজি
    0.42
     Section
    0.42
     immediacy
    0.42
    POSITIVE LOGITS
     margen
    0.50
     धूप
    0.49
     dan
    0.48
     Lotion
    0.47
     koncept
    0.47
    nya
    0.47
    朊
    0.47
     zvol
    0.46
     बंद
    0.45
    يين
    0.45
    Activations Density 0.003%

    No Known Activations