© 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. 126630
    Prev
    Next
    INDEX
    Explanations

    specification

    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
    Aqu
    0.45
    Flor
    0.45
    Host
    0.44
    Push
    0.44
    Cas
    0.44
    Gro
    0.43
    B
    0.43
     ዕ
    0.42
    J
    0.42
    Flower
    0.41
    POSITIVE LOGITS
    ឫ
    0.47
     dentro
    0.46
     ocult
    0.46
    рен
    0.46
     oportun
    0.46
     identific
    0.46
     kontrol
    0.45
     reven
    0.45
     asoci
    0.45
     Darstellung
    0.45
    Activations Density 0.003%

    No Known Activations