© 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. 101167
    Prev
    Next
    INDEX
    Explanations

    specific nouns followed by context

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

    ur mom joke

    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
    られる
    0.41
     Ensures
    0.41
     دیے
    0.41
    ır
    0.40
    delà
    0.40
    ě
    0.39
    ter
    0.38
    മാക്കി
    0.38
     contiguous
    0.37
     paltry
    0.37
    POSITIVE LOGITS
     governador
    0.55
     abril
    0.54
     maio
    0.54
    框
    0.52
     adicion
    0.52
     春
    0.52
     添加
    0.52
     把
    0.52
     colegas
    0.52
     mc
    0.51
    Activations Density 0.000%

    No Known Activations