© 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. 222212
    Prev
    Next
    INDEX
    Explanations

    medical, financial, or technical terms

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

    foreign words and technical terms

    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
    at
    0.47
    ỏe
    0.44
    NG
    0.44
    6
    0.44
    af
    0.44
     Caball
    0.43
    vi
    0.43
    یه
    0.43
     obtuvo
    0.43
    inat
    0.42
    POSITIVE LOGITS
    跎
    0.53
    شي
    0.50
    咐
    0.50
    كي
    0.49
    やつ
    0.47
    まさ
    0.47
     husky
    0.47
    zingen
    0.46
    дения
    0.46
     BABY
    0.46
    Activations Density 0.001%

    No Known Activations