© 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. 143855
    Prev
    Next
    INDEX
    Explanations

    certifying thisregarding ayour employees

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

    generation, quantum, source, Asi

    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
     можем
    0.61
    بيرة
    0.59
    ويم
    0.55
    郃
    0.55
    اليه
    0.53
    ємо
    0.53
    আমাকে
    0.52
    मैंने
    0.50
    高
    0.50
    ackerel
    0.49
    POSITIVE LOGITS
     rong
    0.50
     terl
    0.46
     cis
    0.44
     formalism
    0.44
     dan
    0.44
     radiolysis
    0.44
     LEED
    0.43
     y
    0.42
     radi
    0.42
     feng
    0.42
    Activations Density 0.001%

    No Known Activations