© 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. 57190
    Prev
    Next
    INDEX
    Explanations

    latest episode

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

    quality, stability, improvements

    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
     basura
    0.44
     subpoenas
    0.44
    acciones
    0.44
    ೂರಿನ
    0.44
     विजयी
    0.43
    我会
    0.43
    ঞ্চলিক
    0.42
    嗄
    0.42
     инструментов
    0.42
    ಹಿ
    0.42
    POSITIVE LOGITS
     inclu
    0.43
     అది
    0.42
     Including
    0.42
     கொண்டுள்ளது
    0.42
    ná
    0.41
     including
    0.40
     advantageous
    0.40
     entreprise
    0.40
     וכ
    0.40
     fator
    0.40
    Activations Density 0.000%

    No Known Activations