© 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-65K
    7. 63861
    Prev
    Next
    INDEX
    Explanations

    know everything

    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
     cũ
    0.59
     hilang
    0.52
     eski
    0.49
    ü
    0.49
     marred
    0.49
     hilar
    0.47
    ũ
    0.47
     ancak
    0.46
    रील
    0.46
     entrando
    0.46
    POSITIVE LOGITS
    Shares
    0.45
    cyt
    0.44
    Maps
    0.43
    ETER
    0.43
    Space
    0.41
    lights
    0.41
    在
    0.41
    ETERS
    0.41
    Rules
    0.40
    Storyboard
    0.40
    Activations Density 0.006%

    No Known Activations