© 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. 194583
    Prev
    Next
    INDEX
    Explanations

    article, if, write, LORD, line, business

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

    ethical considerations

    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
    phalodes
    0.45
    texto
    0.44
     lectured
    0.42
    ί
    0.42
    avras
    0.42
     विज्ञ
    0.42
    zuf
    0.41
     behaved
    0.40
     Mellon
    0.40
    esgue
    0.39
    POSITIVE LOGITS
    ช่วย
    0.48
     redesigned
    0.47
    /
    0.47
     anniversary
    0.47
     redesign
    0.46
    彻
    0.46
    膊
    0.46
    JOB
    0.46
    ประจำ
    0.46
     Rong
    0.45
    Activations Density 0.002%

    No Known Activations