© 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. 160170
    Prev
    Next
    INDEX
    Explanations

    students will, long ago

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

    steps and processes

    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
    ية
    0.63
    ien
    0.55
    ^\
    0.55
    ol
    0.53
    _
    0.52
    orie
    0.52
    ai
    0.50
    ina
    0.50
     gelin
    0.48
    yr
    0.48
    POSITIVE LOGITS
    蟎
    0.49
    摑
    0.48
     CARL
    0.48
    鐸
    0.47
    홧
    0.44
    욤
    0.44
     iodide
    0.43
     cryptography
    0.43
     ブル
    0.42
    ﻔ
    0.42
    Activations Density 0.000%

    No Known Activations