© 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. 49649
    Prev
    Next
    INDEX
    Explanations

    educational institution enrollment

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

    select, finishing, f(n)

    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
    𝒆
    0.48
    cimientos
    0.43
    దల
    0.43
    cesso
    0.42
    োর্ড
    0.41
    वारे
    0.40
    त्तियों
    0.40
    떴
    0.40
    lensFlare
    0.40
    斻
    0.40
    POSITIVE LOGITS
     丶
    0.42
     nub
    0.39
     Dop
    0.38
     nondegenerate
    0.37
     हर्
    0.37
     dew
    0.36
     ''.
    0.36
     دائو
    0.36
     dop
    0.35
     በሚ
    0.35
    Activations Density 0.002%

    No Known Activations