© 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. 55764
    Prev
    Next
    INDEX
    Explanations

    services, provider, professor

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

    provider configurations

    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
    ι
    0.56
    MPs
    0.55
    ické
    0.55
    かね
    0.54
    ی
    0.54
    скую
    0.53
    hares
    0.52
    䢎
    0.52
    এর
    0.52
    juč
    0.52
    POSITIVE LOGITS
     WHETHER
    0.48
    Provider
    0.47
     ECON
    0.44
     promis
    0.43
    Ownership
    0.43
    Owner
    0.41
     Provider
    0.40
     renderer
    0.39
     SBC
    0.39
     covariant
    0.39
    Activations Density 0.001%

    No Known Activations