© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11439
    Prev
    Next
    INDEX
    Explanations

    describes or calculates standardized concepts

    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
     seedlings
    0.42
     verily
    0.41
     Maret
    0.41
    grunge
    0.41
    akespeare
    0.41
    renergic
    0.41
    lamide
    0.41
    ۴
    0.40
     znale
    0.39
    oseconds
    0.39
    POSITIVE LOGITS
     assumes
    0.54
     padrão
    0.49
     calculates
    0.47
     Calculates
    0.46
     estándar
    0.45
    經典
    0.45
     использованием
    0.42
     Includes
    0.42
     básico
    0.42
    式的
    0.42
    Activations Density 0.001%

    No Known Activations