© 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. 87384
    Prev
    Next
    INDEX
    Explanations

    your service or owner

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

    ***and is

    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
    立方
    0.56
     过
    0.52
    tensor
    0.50
    方形
    0.49
     则
    0.49
     主要
    0.49
    朲
    0.48
    toggle
    0.48
    वार
    0.47
    राधना
    0.47
    POSITIVE LOGITS
     Sarm
    0.47
     hillside
    0.45
    んですよ
    0.45
    ب
    0.45
     gearing
    0.44
    ราบ
    0.44
     villages
    0.43
     alde
    0.43
    ش
    0.43
     scouring
    0.42
    Activations Density 0.000%

    No Known Activations