© 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. 154456
    Prev
    Next
    INDEX
    Explanations

    Samsung Gear

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

    ECC RAM errors

    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
    PSY
    0.50
    飛
    0.49
     Такие
    0.49
     同じ
    0.48
     ਸਰ
    0.48
     強
    0.47
     効果
    0.47
    粞
    0.47
    下の
    0.47
     時計
    0.46
    POSITIVE LOGITS
     dịp
    0.48
    rater
    0.47
     standart
    0.47
    ä
    0.47
     paragra
    0.46
    上市公司
    0.45
     thì
    0.44
    osterone
    0.43
     holl
    0.42
    aków
    0.42
    Activations Density 0.001%

    No Known Activations