© 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. 39297
    Prev
    Next
    INDEX
    Explanations

    largest inventory or up to

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

    formulas and definitions

    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
     बचें
    0.44
     வாழ்வில்
    0.44
    㷫
    0.44
    🥴
    0.44
    😞
    0.43
     nostalg
    0.43
    yana
    0.42
     Huyền
    0.42
    💫
    0.42
    😑
    0.42
    POSITIVE LOGITS
     jurisdiction
    0.44
    bd
    0.43
    owe
    0.39
    id
    0.39
     जर
    0.38
    교
    0.38
    asty
    0.37
    ovi
    0.37
    rien
    0.36
     справо
    0.36
    Activations Density 0.001%

    No Known Activations