© 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. 149136
    Prev
    Next
    INDEX
    Explanations

    legislation and forward

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

    contextual information

    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
     угро
    0.52
     exager
    0.49
    ༩
    0.47
    λλην
    0.46
     कष्ट
    0.45
    (__('
    0.45
     բ
    0.45
     счета
    0.45
    츨
    0.44
    akespeare
    0.44
    POSITIVE LOGITS
     compatibility
    0.48
     supervisory
    0.48
     compatible
    0.47
     biodiesel
    0.46
    াজ
    0.46
     veterinarian
    0.46
     cybersecurity
    0.45
     raft
    0.45
     package
    0.45
     bestselling
    0.45
    Activations Density 0.000%

    No Known Activations