© 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. 109686
    Prev
    Next
    INDEX
    Explanations

    following spring’s

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

    explaining concepts and roles

    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
     deportivas
    0.45
    linger
    0.44
     zwölf
    0.44
    ként
    0.43
    )}+\
    0.43
    anger
    0.43
     meubles
    0.43
     Alpes
    0.43
    auch
    0.42
     neun
    0.42
    POSITIVE LOGITS
    nnc
    0.51
     মাস
    0.49
    魇
    0.49
     datetime
    0.46
     अथ
    0.46
    UTORY
    0.46
     calibration
    0.46
     মাসের
    0.46
    CTED
    0.45
    ფორმა
    0.44
    Activations Density 0.001%

    No Known Activations