© 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. 95725
    Prev
    Next
    INDEX
    Explanations

    some ... of them, others

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

    personal names and media labels

    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
    ابی
    0.42
    amer
    0.41
    ilation
    0.39
     друго
    0.39
    ی
    0.39
     Retrieved
    0.38
    മില്ല
    0.37
     appare
    0.37
     entered
    0.37
     Weltkrieg
    0.36
    POSITIVE LOGITS
    🫰
    0.51
    ᵔ
    0.50
    𝘃
    0.47
     ২০২৩
    0.46
    startsWith
    0.46
    禮
    0.45
    נג
    0.45
     ChatGPT
    0.45
     juicio
    0.45
    ChatGPT
    0.45
    Activations Density 0.000%

    No Known Activations