© 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. 202069
    Prev
    Next
    INDEX
    Explanations

    new brand, his own, our site

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

    structure, interface, or category

    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
    ten
    0.58
    Tinh
    0.52
    T
    0.50
    breakfast
    0.50
    friends
    0.49
    goods
    0.47
    hostname
    0.47
     Identities
    0.47
    non
    0.46
    I
    0.46
    POSITIVE LOGITS
    حدة
    0.51
     abruptly
    0.50
     dreary
    0.49
     glared
    0.49
     flamboyant
    0.48
     ante
    0.48
     hurriedly
    0.47
     descenso
    0.47
     bruised
    0.46
     shrug
    0.46
    Activations Density 0.000%

    No Known Activations