© 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. 25980
    Prev
    Next
    INDEX
    Explanations

    brand followed by model or code

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

    specific details

    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
    :
    0.61
    P
    0.51
    W
    0.48
    !
    0.46
    n
    0.44
    l
    0.44
    PSD
    0.44
    -
    0.44
    I
    0.44
    HP
    0.44
    POSITIVE LOGITS
    ່ນ
    0.59
     Paryayvachi
    0.54
     παιδιά
    0.54
    󰡕
    0.53
     περισ
    0.52
     примеру
    0.52
     آئے
    0.51
     положи
    0.51
     деца
    0.50
     लड़कियों
    0.50
    Activations Density 0.000%

    No Known Activations