© 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. 23076
    Prev
    Next
    INDEX
    Explanations

    God dried, fractures isn’t, reprising, read my

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

    symbols or punctuation

    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
    ை
    0.45
    显然
    0.42
    бор
    0.42
    жу
    0.41
     культуры
    0.41
     высокой
    0.41
     простой
    0.41
    શિ
    0.40
     иной
    0.39
    ванных
    0.38
    POSITIVE LOGITS
     Schaefer
    0.44
     Napoleon
    0.43
     cytologic
    0.43
     inciner
    0.42
     F
    0.41
     enne
    0.41
     Arx
    0.41
     mountain
    0.41
     dyslex
    0.41
     herpes
    0.40
    Activations Density 0.000%

    No Known Activations