© 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. 5142
    Prev
    Next
    INDEX
    Explanations

    academic citations and DOIs

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

    links to scientific articles

    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
    Zobacz
    0.55
    vykor
    0.52
    ཥ
    0.51
    WhiteRatingDiff
    0.50
     wikipagina
    0.50
     lymphatiques
    0.50
     olyan
    0.49
    Methylsulfanyl
    0.49
     interstitiis
    0.48
     grosseur
    0.48
    POSITIVE LOGITS
    ’
    0.65
    we
    0.63
    ne
    0.59
     and
    0.58
    j
    0.57
    C
    0.55
    ot
    0.54
    per
    0.54
    .
    0.54
    ac
    0.52
    Activations Density 0.012%

    No Known Activations