© 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. 80735
    Prev
    Next
    INDEX
    Explanations

    method of transmission

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

    backticks

    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
    ↵↵
    0.53
    0.46
     größ
    0.46
    inken
    0.46
    heavy
    0.44
    <sup>
    0.44
     manchmal
    0.44
    '
    0.44
    ↵↵↵↵↵
    0.43
     paren
    0.43
    POSITIVE LOGITS
     युवाओ
    0.50
    ジネス
    0.48
     giỏi
    0.48
    yatiti
    0.47
    における
    0.47
    юсь
    0.46
    тың
    0.46
    ubjects
    0.45
    ፁ
    0.45
    ፆ
    0.45
    Activations Density 0.004%

    No Known Activations