© 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. 60226
    Prev
    Next
    INDEX
    Explanations

    Visitors and orders

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

    examples and "say"

    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
     ya
    0.46
    يس
    0.45
     física
    0.45
    物理
    0.45
    ↵↵
    0.44
    ون
    0.44
    ینس
    0.44
    ↵↵↵
    0.44
    берите
    0.44
    سب
    0.44
    POSITIVE LOGITS
    ｭ
    0.52
     Infatti
    0.49
     വന്ന
    0.49
     মিটিং
    0.48
     Inoltre
    0.46
    ו
    0.46
     தொடங்கியது
    0.45
    ㍍
    0.45
    ונה
    0.45
    ঁচ
    0.45
    Activations Density 0.000%

    No Known Activations