© 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-65K
    7. 61743
    Prev
    Next
    INDEX
    Explanations

    list indices and arguments

    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_65k_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
    0.66
     estar
    0.59
     k
    0.59
     pompe
    0.59
     م
    0.57
     ک
    0.56
     m
    0.54
     מ
    0.54
     commentators
    0.54
     v
    0.54
    POSITIVE LOGITS
    ició
    0.45
    itz
    0.44
     болезнь
    0.43
    getImage
    0.43
    гор
    0.42
    েন্দ্রলাল
    0.42
    င
    0.41
    fireFlower
    0.40
    갛
    0.39
    зиру
    0.39
    Activations Density 0.012%

    No Known Activations