© 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. 223022
    Prev
    Next
    INDEX
    Explanations

    helps remind

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

    honoring filters

    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
    IRCONIUM
    0.50
    \
    0.50
    生徒
    0.46
    াদেশিক
    0.45
    所谓
    0.44
    假设
    0.44
    OLE
    0.44
     faculties
    0.44
     স্কুলে
    0.43
    τον
    0.43
    POSITIVE LOGITS
    ಣ
    0.52
    ramento
    0.50
    i
    0.50
     Short
    0.49
    at
    0.46
     Strang
    0.46
    array
    0.45
    adat
    0.44
    value
    0.44
     Governo
    0.44
    Activations Density 0.000%

    No Known Activations