© 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. 7498
    Prev
    Next
    INDEX
    Explanations

    Go package flags

    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
    lickr
    0.23
    4
    0.22
    2
    0.21
     incluido
    0.21
    ત
    0.21
    迅速
    0.21
    വും
    0.20
    ágico
    0.20
    の
    0.20
    9
    0.20
    POSITIVE LOGITS
     testAvg
    0.22
    Ꮡ
    0.20
    ുവരി
    0.20
     memeriksa
    0.20
     mathbf
    0.20
    <unused1100>
    0.19
     prudence
    0.19
     inspe
    0.19
     從
    0.19
    曉
    0.19
    Activations Density 0.001%

    No Known Activations