© 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. 193484
    Prev
    Next
    INDEX
    Explanations

    secrets of success

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

    arrival, miles, open, pistachios

    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
     disant
    0.43
    Myanmar
    0.43
     Lancet
    0.42
    Afghanistan
    0.40
     Bundestag
    0.40
     </
    0.40
    .*
    0.40
    viewDidLoad
    0.40
     "[
    0.39
    expansion
    0.39
    POSITIVE LOGITS
    setNome
    0.48
     별
    0.47
    曛
    0.45
     मिठ
    0.45
     сами
    0.44
    职业
    0.43
     சர்ச்ச
    0.43
    anst
    0.42
     חד
    0.42
     נוס
    0.42
    Activations Density 0.000%

    No Known Activations