© 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. 134809
    Prev
    Next
    INDEX
    Explanations

    cure time

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

    technical terms and specifics

    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
    word
    0.51
    <0x0D>
    0.50
    NESS
    0.50
    ckt
    0.50
    招
    0.48
    CROSS
    0.47
     Modules
    0.47
    Y
    0.46
    1
    0.45
    n
    0.44
    POSITIVE LOGITS
    дно
    0.46
     కార్యక్రమంలో
    0.46
    ﺔ
    0.46
     चेन्नई
    0.45
    ྩ
    0.44
     prostaglandins
    0.44
     programação
    0.44
     권
    0.43
    ुलकर
    0.43
     కార్యక్ర
    0.43
    Activations Density 0.000%

    No Known Activations