© 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. 197965
    Prev
    Next
    INDEX
    Explanations

    coming from, chance to, starting with, comparable quarter

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

    automated parking assist

    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
    brook
    0.51
    I
    0.50
    auction
    0.49
    毓
    0.48
    看待
    0.46
    aching
    0.46
    嫵
    0.46
    personal
    0.45
     PERSONAL
    0.45
     мушка
    0.45
    POSITIVE LOGITS
     dereg
    0.49
     règlement
    0.48
     buzzer
    0.48
    \%$
    0.46
     basée
    0.46
     botón
    0.46
    争
    0.46
     souhait
    0.45
     tél
    0.45
     freer
    0.45
    Activations Density 0.001%

    No Known Activations