© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 114877
    Prev
    Next
    INDEX
    Explanations

    Estonian branch, question goes, not necessary

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

    grading student assignment

    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
    ון
    0.47
    )&
    0.47
    roku
    0.45
    νας
    0.43
    "${
    0.42
    ել
    0.41
    னைய
    0.41
    陰
    0.41
    πος
    0.40
     digestible
    0.40
    POSITIVE LOGITS
     è
    0.48
     بیل
    0.44
     são
    0.44
     â
    0.44
     Gulf
    0.43
     utilisées
    0.42
     sân
    0.42
     Pensacola
    0.42
     Football
    0.41
     È
    0.41
    Activations Density 0.000%

    No Known Activations