© 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. 42247
    Prev
    Next
    INDEX
    Explanations

    dog loves. tell. site. Xen. make. rappers

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

    talking, sounds, API, refrigerant

    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
     озеро
    0.45
    贰百
    0.44
     তোলেন
    0.44
     নিজেদের
    0.43
    ᱞ
    0.42
     از
    0.42
     اور
    0.42
    शंकर
    0.42
     மலை
    0.41
     اخر
    0.41
    POSITIVE LOGITS
    actually
    0.44
     actually
    0.43
    クロ
    0.43
    techn
    0.43
    tedy
    0.43
    certified
    0.43
    but
    0.42
     iyong
    0.41
    }^{*
    0.41
     infliction
    0.40
    Activations Density 0.000%

    No Known Activations