© 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. 16506
    Prev
    Next
    INDEX
    Explanations

    prepositions and pronouns followed by punctuation

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

    asking about what

    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
    on
    0.33
     จึง
    0.31
    an
    0.29
    available
    0.29
    N
    0.29
    annotation
    0.28
    atribut
    0.28
    G
    0.28
    agation
    0.28
    confirmed
    0.27
    POSITIVE LOGITS
     is
    0.30
    hhhhhhhh
    0.29
    ني
    0.28
     nich
    0.28
    咳
    0.28
    긔
    0.27
    hhh
    0.27
    )]=
    0.27
    ルイ
    0.27
    ぼ
    0.27
    Activations Density 0.235%

    No Known Activations