© 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. 23924
    Prev
    Next
    INDEX
    Explanations

    processing of data

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

    occurred after, symptoms, obtain

    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
    toFloat
    0.45
     구성
    0.43
     Converting
    0.42
     ஜூ
    0.42
     ()=>{
    0.41
     مكون
    0.41
     Pursuant
    0.41
     программ
    0.40
    кия
    0.40
     Tack
    0.40
    POSITIVE LOGITS
    line
    0.46
    _
    0.46
    ensus
    0.45
    σε
    0.44
     generasi
    0.41
    EOUT
    0.41
     ambao
    0.40
    <
    0.40
    È
    0.40
    Œ
    0.40
    Activations Density 0.000%

    No Known Activations