© 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. 126770
    Prev
    Next
    INDEX
    Explanations

    place names and routes

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

    because of, single epidemic, acquired for

    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
     OPERATIONS
    0.48
     musical
    0.47
    샥
    0.45
    OUSE
    0.45
     MEP
    0.45
    افل
    0.45
    집합
    0.44
    πως
    0.43
    PLICATIONS
    0.43
     modifica
    0.43
    POSITIVE LOGITS
    ten
    0.55
    ä
    0.50
    だし
    0.50
    king
    0.50
    ána
    0.47
     मसाला
    0.45
    ong
    0.44
    បាន
    0.44
    ettle
    0.43
    เตอร์
    0.43
    Activations Density 0.001%

    No Known Activations