© 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. 175353
    Prev
    Next
    INDEX
    Explanations

    non-English text

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

    println was ongoing

    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
    fortune
    0.58
    ard
    0.52
     admire
    0.48
     admiration
    0.47
     admiring
    0.47
     cheerfully
    0.46
     ആരാധ
    0.46
    곧
    0.46
     admirers
    0.45
     sweetly
    0.45
    POSITIVE LOGITS
     atual
    0.50
     piernas
    0.47
     drogas
    0.46
     ruedas
    0.46
     शॉर्ट
    0.46
     '':
    0.45
     분
    0.45
    랑
    0.45
    ॉजिस्ट
    0.44
     комна
    0.44
    Activations Density 0.000%

    No Known Activations