© 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. 40-GEMMASCOPE-2-RES-65K
    7. 49481
    Prev
    Next
    INDEX
    Explanations

    physical and visual descriptors

    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_40_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
    တီ
    0.45
    最初は
    0.37
    ﾂ
    0.36
    私募
    0.35
    ’-
    0.35
     Polynesia
    0.35
    >("
    0.34
    ])+
    0.34
     subjectivity
    0.34
    㭉
    0.34
    POSITIVE LOGITS
    భవ
    0.44
    Nit
    0.43
     Kin
    0.43
     忄
    0.41
     increases
    0.39
    etor
    0.39
    Kin
    0.39
    brains
    0.39
     erhöht
    0.38
     ওঠ
    0.38
    Activations Density 0.002%

    No Known Activations