© 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. 251795
    Prev
    Next
    INDEX
    Explanations

    domain hosting, state vaccination, get one

    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
     ପ୍ର
    0.55
     prur
    0.53
    ডির
    0.53
    μού
    0.47
    orgement
    0.46
     narrower
    0.46
    \|_{\
    0.46
     पद्धति
    0.46
     ধাত
    0.45
     hepatic
    0.44
    POSITIVE LOGITS
     почи
    0.51
    h
    0.50
    d
    0.47
    fica
    0.47
    x
    0.47
    t
    0.46
    r
    0.46
    n
    0.45
    ícia
    0.45
     сложно
    0.45
    Activations Density 0.000%

    No Known Activations