© 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. 8355
    Prev
    Next
    INDEX
    Explanations

    necessary contact nasals

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

    VS Code, voice, Material

    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
     pInBuffer
    0.49
    厚生
    0.46
    ᱝ
    0.45
    いろいろ
    0.44
    ন
    0.44
    आम
    0.43
    手を
    0.43
    नए
    0.43
     उद्यमियों
    0.43
    (),
    0.42
    POSITIVE LOGITS
     pinpoint
    0.45
     wild
    0.44
     Jun
    0.44
     seiner
    0.43
     option
    0.43
     console
    0.42
     sortie
    0.41
     standout
    0.41
     High
    0.41
     deiner
    0.41
    Activations Density 0.000%

    No Known Activations