© 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. 211106
    Prev
    Next
    INDEX
    Explanations

    writing documents

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

    opposite of and nuance

    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
    féle
    0.51
     दर्
    0.47
     електрон
    0.46
     दिवाळी
    0.46
     próximas
    0.45
     elektronic
    0.45
    戬
    0.44
    登记
    0.43
     ಮಕ್ಕಳ
    0.43
    莴
    0.42
    POSITIVE LOGITS
    )':
    0.46
    contrad
    0.45
    alignat
    0.44
    a
    0.44
    ᾖ
    0.44
    ा
    0.42
    ূন্য
    0.41
    бари
    0.41
    cian
    0.41
     equates
    0.41
    Activations Density 0.000%

    No Known Activations