© 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. 24054
    Prev
    Next
    INDEX
    Explanations

    descriptions and lists

    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
     grav
    0.46
     e
    0.44
     polka
    0.42
     elev
    0.42
     rise
    0.41
     pet
    0.41
     hoi
    0.40
     liv
    0.40
     hai
    0.40
     sy
    0.40
    POSITIVE LOGITS
    clature
    0.50
    ō
    0.46
    КО
    0.46
    섞
    0.46
    Ｐ
    0.45
    아
    0.43
    텍
    0.42
    ປະກອບ
    0.41
     Amplifier
    0.41
    ewnątrz
    0.40
    Activations Density 0.001%

    No Known Activations