© 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. 43535
    Prev
    Next
    INDEX
    Explanations

    all followed by a word

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

    coding compass, alien, file object, body inflation, compression

    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
     pulgadas
    0.47
     SHIPPING
    0.46
     la
    0.45
     recollection
    0.45
     adrenaline
    0.45
     carnage
    0.44
     մաս
    0.44
    }$\
    0.43
     boast
    0.43
    ことも
    0.43
    POSITIVE LOGITS
    ziła
    0.55
    中医
    0.48
    Ḫ
    0.46
     Disposition
    0.45
    terna
    0.44
    thouse
    0.44
     ToolsVersion
    0.44
    rahydro
    0.43
    ésar
    0.43
    paw
    0.43
    Activations Density 0.000%

    No Known Activations