© 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. 73202
    Prev
    Next
    INDEX
    Explanations

    monthly payment

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

    goat

    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
    Ա
    0.47
    А
    0.46
    fdata
    0.46
    Чита
    0.46
    aruhi
    0.46
    tir
    0.46
    Но
    0.45
    parametri
    0.45
    Де
    0.45
    onesian
    0.45
    POSITIVE LOGITS
    按钮
    0.52
     轻
    0.46
     用于
    0.46
     மற்றும்
    0.44
     khung
    0.44
     Crouch
    0.44
    两侧
    0.43
     και
    0.43
     शैली
    0.43
     不要
    0.43
    Activations Density 0.002%

    No Known Activations