© 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. 17917
    Prev
    Next
    INDEX
    Explanations

    articles followed by nouns

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

    over the lastlast decadeover the pastpast decadesover yearslast 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
    Wifi
    0.41
    SWE
    0.41
     簡単
    0.38
     خواب
    0.37
     tohoto
    0.37
    EVENT
    0.37
    GRA
    0.37
    흙
    0.37
     ዘዴ
    0.37
    Paddle
    0.37
    POSITIVE LOGITS
     its
    0.45
     seu
    0.39
     his
    0.39
    meets
    0.39
     خلال
    0.39
     stylistic
    0.38
     thematic
    0.38
     acclaimed
    0.38
     ее
    0.37
     pursuant
    0.37
    Activations Density 0.037%

    No Known Activations