© 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. 61586
    Prev
    Next
    INDEX
    Explanations

    customer frustrations and prosecutor allegedly

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

    describing specific activities or states

    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
    m
    0.51
    小编
    0.47
     escuela
    0.44
    空格
    0.44
     banderas
    0.42
    sp
    0.42
    િક્
    0.42
    半
    0.42
     ellos
    0.42
     iluminación
    0.41
    POSITIVE LOGITS
     akin
    0.46
     alluded
    0.46
     우선
    0.46
    osis
    0.46
     treasured
    0.46
     tantamount
    0.45
     보도록
    0.44
     తాను
    0.43
    ICs
    0.43
    oprol
    0.43
    Activations Density 0.000%

    No Known Activations