© 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. 180519
    Prev
    Next
    INDEX
    Explanations

    around a single parent star

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

    creating formats or structures

    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
     zejména
    0.50
    皘
    0.48
    mér
    0.47
    ęła
    0.46
     Mayıs
    0.43
     przen
    0.43
    ůže
    0.43
    mě
    0.42
    Conse
    0.42
    agat
    0.42
    POSITIVE LOGITS
     \
    0.46
     saving
    0.45
     farmed
    0.44
     than
    0.43
     football
    0.41
     Bundesliga
    0.41
     or
    0.41
     space
    0.40
     alignment
    0.40
    封面
    0.40
    Activations Density 0.000%

    No Known Activations