© 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. 159659
    Prev
    Next
    INDEX
    Explanations

    create future cooperation

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

    question forces, Tiber carefully

    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
    iale
    0.46
    interrupt
    0.46
    amphetamine
    0.45
     ଶ
    0.45
     изучение
    0.45
     මා
    0.44
     प्रत्यक्ष
    0.44
    <0xA7>
    0.43
    ubjects
    0.43
     மேற்கொண்ட
    0.43
    POSITIVE LOGITS
    сія
    0.53
     hangar
    0.50
    FromThe
    0.50
     relic
    0.50
    트에
    0.49
     Atlantis
    0.48
    킹
    0.46
     Vereinig
    0.46
    ەس
    0.46
     tilts
    0.45
    Activations Density 0.000%

    No Known Activations