© 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. 161370
    Prev
    Next
    INDEX
    Explanations

    numbers and associated words like 4

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

    world-building and inspired glamour

    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
    \]
    0.52
     protokol
    0.51
    >]
    0.49
     novella
    0.47
    ik
    0.46
     जग
    0.45
     ॥
    0.45
     diskut
    0.45
    难
    0.44
     =",
    0.44
    POSITIVE LOGITS
    сү
    0.58
    compensation
    0.48
    Cors
    0.45
    Qaeda
    0.44
    Xs
    0.44
    உங்கள்
    0.44
    maschine
    0.43
    s
    0.43
    们的
    0.43
     Бүген
    0.43
    Activations Density 0.001%

    No Known Activations