© 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. 151883
    Prev
    Next
    INDEX
    Explanations

    opening quotes followed by common sentence starters

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

    ¡Claro! or similar affirmatives

    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
     (
    0.67
     ("
    0.58
     (.
    0.58
     veía
    0.54
     («
    0.54
     (“
    0.53
     drei
    0.52
     quarts
    0.52
     “”
    0.52
     tiga
    0.51
    POSITIVE LOGITS
    ReadOnly
    0.50
     dwind
    0.49
    stopPropagation
    0.48
    S
    0.48
    A
    0.48
    zahl
    0.45
    ನಿರ್
    0.44
    стати
    0.44
    мен
    0.44
    водитель
    0.44
    Activations Density 0.076%

    No Known Activations