© 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. 134819
    Prev
    Next
    INDEX
    Explanations

    geographic and abstract concepts

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

    strategies for

    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
     Autobiography
    0.45
    ත්‍ර
    0.43
     ఒక్క
    0.42
     autorizado
    0.42
     deterioro
    0.42
    力度
    0.41
     faraway
    0.41
    孩
    0.41
     descub
    0.40
    去做
    0.40
    POSITIVE LOGITS
     також
    0.48
     جنگ
    0.48
     ज्ञात
    0.45
    isher
    0.45
     глава
    0.43
     जु
    0.43
    toe
    0.42
     반응
    0.42
    M
    0.42
     Dex
    0.41
    Activations Density 0.001%

    No Known Activations