© 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. 55725
    Prev
    Next
    INDEX
    Explanations

    subject to change

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

    than comparable

    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
     عكس
    0.46
     sickening
    0.46
     oversees
    0.45
     regionally
    0.45
     এলাকায়
    0.43
     oversee
    0.42
     overse
    0.42
    𝖺
    0.42
     gute
    0.41
    וס
    0.41
    POSITIVE LOGITS
    parametric
    0.48
    Than
    0.43
    Bea
    0.43
    рованные
    0.42
    Jamaica
    0.42
    y
    0.42
    A
    0.41
    Panic
    0.41
    FFFF
    0.40
    Crystal
    0.40
    Activations Density 0.000%

    No Known Activations