© 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. 115731
    Prev
    Next
    INDEX
    Explanations

    Original Touch features

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

    predictive text engines

    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
    <unused23>
    0.57
     pedibus
    0.51
     Ausdruck
    0.50
    íonn
    0.48
     Frente
    0.47
    ロー
    0.47
     pedibusque
    0.47
    통령
    0.46
    カテゴ
    0.46
    ѓ
    0.46
    POSITIVE LOGITS
     covid
    0.49
     COVID
    0.49
    COVID
    0.47
    man
    0.45
    covid
    0.45
     కరో
    0.45
    විත
    0.44
     kond
    0.43
     אשר
    0.43
     polling
    0.43
    Activations Density 0.000%

    No Known Activations