© 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. 61457
    Prev
    Next
    INDEX
    Explanations

    off or copy

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

    undermines, designed, focused

    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
    距离
    0.50
     both
    0.44
    最为
    0.44
    两侧
    0.44
    गर
    0.44
     Há
    0.43
    悝
    0.43
     Pads
    0.43
     Delay
    0.42
    煨
    0.42
    POSITIVE LOGITS
     ejempl
    0.48
    pdf
    0.45
    ohex
    0.44
     propone
    0.43
    qc
    0.43
     опа
    0.43
     esiste
    0.43
    効率
    0.43
    olem
    0.42
    オーク
    0.42
    Activations Density 0.002%

    No Known Activations