© 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. 131707
    Prev
    Next
    INDEX
    Explanations

    common word transitions

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

    identifying the premise

    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
     Cint
    0.52
     Âu
    0.50
     civilized
    0.46
     cilt
    0.44
    ົ
    0.44
    गर्
    0.44
    гам
    0.44
    銖
    0.44
     செயல்பா
    0.43
     whirling
    0.43
    POSITIVE LOGITS
     অন্ধকার
    0.44
    steacher
    0.43
     enkelt
    0.43
    clipse
    0.42
     atteinte
    0.42
    Pra
    0.42
    umon
    0.42
    Commande
    0.42
    erm
    0.41
    তনে
    0.41
    Activations Density 0.001%

    No Known Activations