© 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. 184807
    Prev
    Next
    INDEX
    Explanations

    people and their roles

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

    LaTeX code with packages

    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
    сова
    0.42
    魂
    0.41
    یکم
    0.40
    夏
    0.40
     प्रदर्शन
    0.40
    พล
    0.39
     ایس
    0.39
    нина
    0.38
    謦
    0.38
    Segoe
    0.38
    POSITIVE LOGITS
    র্
    0.47
     totales
    0.46
     Ejemplo
    0.43
     hinzufügen
    0.41
     Kc
    0.41
     LENGTH
    0.41
    cientes
    0.41
     creación
    0.41
     ರಚ
    0.41
    output
    0.40
    Activations Density 0.000%

    No Known Activations