© 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. 226238
    Prev
    Next
    INDEX
    Explanations

    English subtitles

    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
     تساوي
    0.48
    वान
    0.45
     князя
    0.44
    InCM
    0.43
     ама
    0.42
     senador
    0.42
    嫒
    0.42
    लिड
    0.42
     मौर्य
    0.42
    AllResult
    0.41
    POSITIVE LOGITS
    ')){
    0.48
    กระ
    0.44
    tokenize
    0.44
    umis
    0.44
    ubo
    0.43
     recommandé
    0.43
    illator
    0.43
    )){
    0.42
    appointment
    0.42
     familiarize
    0.42
    Activations Density 0.003%

    No Known Activations