© 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. 175308
    Prev
    Next
    INDEX
    Explanations

    other languages and English

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

    mention your, secretly preparing, mind is, something about, not punishment, for future

    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
    га
    0.49
    estellten
    0.48
    rody
    0.47
    rement
    0.47
     מא
    0.46
     ד
    0.46
     kann
    0.45
    エンド
    0.45
     რე
    0.45
    represents
    0.45
    POSITIVE LOGITS
     samano
    0.46
    挖
    0.45
     residencial
    0.45
    োর
    0.44
     ukup
    0.42
    ంబేద్కర్
    0.42
     következő
    0.41
    ত্রী
    0.41
     comuna
    0.40
     miejscowości
    0.40
    Activations Density 0.000%

    No Known Activations