© 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. 218843
    Prev
    Next
    INDEX
    Explanations

    opening times, stopping at, train stops

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

    AI is not magic

    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
    ektor
    0.48
    '
    0.47
    orems
    0.45
    ‘
    0.45
    enuh
    0.44
    "
    0.44
    లె
    0.43
    azin
    0.43
    आईए
    0.42
    ajat
    0.42
    POSITIVE LOGITS
     rescu
    0.54
     CHEM
    0.49
     rescued
    0.49
    anyu
    0.48
     примерно
    0.47
     Tao
    0.47
     nonprofit
    0.47
    ᐳ
    0.46
    ष्णा
    0.45
     pral
    0.45
    Activations Density 0.000%

    No Known Activations