© 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. 88977
    Prev
    Next
    INDEX
    Explanations

    they were or their

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

    prevents screenshots

    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
     Vorteile
    0.45
     Tore
    0.44
    setMax
    0.44
    Placeholder
    0.44
     Berge
    0.43
     esposo
    0.42
     hore
    0.41
    苻
    0.41
     zorg
    0.41
    Asp
    0.41
    POSITIVE LOGITS
    उनकी
    0.41
    their
    0.40
    assays
    0.40
    ారు
    0.40
    രുവ
    0.40
     Âu
    0.39
     demod
    0.39
     उनका
    0.39
     agreed
    0.38
    Their
    0.38
    Activations Density 0.000%

    No Known Activations