© 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. 84824
    Prev
    Next
    INDEX
    Explanations

    news headlines and official statements

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

    mother would, than usual, how we

    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
     condado
    0.50
     crumpled
    0.49
    깼
    0.46
     Zwischen
    0.46
     rzeczyw
    0.46
    ahun
    0.45
     zunächst
    0.45
    RowFilter
    0.45
     Cutler
    0.45
     прошлом
    0.44
    POSITIVE LOGITS
    Council
    0.46
    Cell
    0.42
    global
    0.40
    every
    0.38
    在全球
    0.38
    ో
    0.38
    രാഷ്ട്ര
    0.37
     Pash
    0.37
    வீன
    0.37
    Brazilian
    0.37
    Activations Density 0.000%

    No Known Activations