© 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-16K
    7. 13217
    Prev
    Next
    INDEX
    Explanations

    percentages and fractions

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

    percentages

    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_16k_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
    ьа
    0.43
    ded
    0.42
    なかなか
    0.40
    )²
    0.40
     menciona
    0.40
    得很
    0.39
     மனை
    0.38
    墊
    0.38
    ırm
    0.38
    ɑ
    0.38
    POSITIVE LOGITS
     Majority
    0.45
    !”
    0.45
     rely
    0.44
     fend
    0.44
    לת
    0.44
     reliant
    0.44
     Ninety
    0.44
    getSt
    0.43
     reliance
    0.43
     Mojo
    0.42
    Activations Density 0.183%

    No Known Activations