© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 99418
    Prev
    Next
    INDEX
    Explanations

    specialized technical specs

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

    Safetensors and efficient formats

    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
     upbringing
    0.47
     Agar
    0.41
     =",
    0.41
     ধারাবাহ
    0.41
    ii
    0.40
     diffusion
    0.40
     contemporaneous
    0.40
     semia
    0.39
     सन्
    0.39
     =,
    0.38
    POSITIVE LOGITS
    ഷ
    0.57
     propriétaires
    0.56
     propriétaire
    0.52
    لات
    0.50
    ل
    0.49
    ométrique
    0.48
    ériel
    0.46
    charg
    0.45
     revenues
    0.44
    urgeon
    0.44
    Activations Density 0.000%

    No Known Activations