© 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. 182857
    Prev
    Next
    INDEX
    Explanations

    its font, other harmful, ; car

    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
     بيكون
    0.54
    า
    0.47
    lin
    0.45
    媲
    0.44
     Full
    0.44
    ون
    0.42
    Packages
    0.42
    Hockey
    0.42
    ů
    0.42
    Sea
    0.42
    POSITIVE LOGITS
     urgently
    0.45
     betray
    0.42
     ながら
    0.41
     metast
    0.41
     ماشینونو
    0.41
     इश्क
    0.41
    Ⲙ
    0.41
     quenched
    0.41
     confront
    0.40
    ក៏
    0.40
    Activations Density 0.000%

    No Known Activations