© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92097
    Prev
    Next
    INDEX
    Explanations

    statistically improbable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    茥
    0.50
     eset
    0.50
     naturelles
    0.49
    ierung
    0.49
    fed
    0.49
    we
    0.47
     Kron
    0.47
    Kron
    0.47
    <unused105>
    0.46
    riteria
    0.46
    POSITIVE LOGITS
     clips
    0.54
     items
    0.50
     heroes
    0.42
     audacity
    0.42
     HERO
    0.42
     bonuses
    0.41
     recipes
    0.41
     Viper
    0.41
     airflow
    0.40
     accomplishments
    0.39
    Activations Density 0.001%

    No Known Activations