© 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. 73347
    Prev
    Next
    INDEX
    Explanations

    funboards follow your list

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

    genre, tales, methodologies, playing

    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
    igraf
    0.48
    ума
    0.48
    늙
    0.47
    负担
    0.46
     courbe
    0.45
    ління
    0.44
    퍼
    0.44
    娉
    0.44
    agal
    0.43
    är
    0.43
    POSITIVE LOGITS
    chk
    0.51
     Investigation
    0.44
    UK
    0.44
    drv
    0.43
     Together
    0.43
    ']}
    0.43
     এছাড়া
    0.43
     ECA
    0.43
     investigation
    0.42
     tale
    0.42
    Activations Density 0.003%

    No Known Activations