© 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. 155317
    Prev
    Next
    INDEX
    Explanations

    hiring vendors and services

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

    pronouns followed by actions or descriptions

    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
     Earl
    0.47
    eb
    0.47
                      
    0.45
     Cort
    0.45
    etan
    0.45
     Mathematics
    0.45
    ur
    0.44
     K
    0.44
     Man
    0.44
     something
    0.44
    POSITIVE LOGITS
    𝙲
    0.46
    ハン
    0.46
    橫
    0.45
    צוע
    0.44
    スペイン
    0.44
    Structures
    0.43
    corresponding
    0.43
    spanish
    0.43
    萨
    0.43
    ټبال
    0.42
    Activations Density 0.001%

    No Known Activations