© 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. 116584
    Prev
    Next
    INDEX
    Explanations

    video conferencing

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

    yields control, hiding, chaotic systems

    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
     చేరు
    0.46
    वाँ
    0.45
    웬
    0.45
    तीय
    0.45
    삵
    0.45
     የአ
    0.44
     trein
    0.44
     Namen
    0.44
     Neces
    0.44
    <0x9F>
    0.43
    POSITIVE LOGITS
    onti
    0.49
     dicha
    0.47
     hai
    0.47
    สอง
    0.46
    üşt
    0.46
    ämp
    0.44
    ก็จะ
    0.44
    Ä
    0.43
    igt
    0.43
    getVideo
    0.42
    Activations Density 0.001%

    No Known Activations