© 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. 14646
    Prev
    Next
    INDEX
    Explanations

    continuation after punctuation

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

    lists of numbers and years

    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
     derived
    0.43
     Mire
    0.38
     Doppler
    0.38
     Markov
    0.37
     Dank
    0.37
     sitter
    0.37
     ܀
    0.37
     ""`
    0.37
     <%=
    0.37
     couche
    0.36
    POSITIVE LOGITS
    វា
    0.45
    वस्था
    0.44
    śred
    0.44
    Drama
    0.43
    Genres
    0.42
    Bulletin
    0.42
    Been
    0.41
     égard
    0.41
    KeyboardView
    0.41
    Diversity
    0.41
    Activations Density 0.000%

    No Known Activations