© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136734
    Prev
    Next
    INDEX
    Explanations

    people think of

    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
    permission
    0.49
    in
    0.49
    warp
    0.48
    payment
    0.47
     놓
    0.47
    estate
    0.47
    property
    0.47
    neighbor
    0.46
    consent
    0.46
    />
    0.45
    POSITIVE LOGITS
     oxalic
    0.52
     atlet
    0.51
     chemot
    0.50
     dificult
    0.49
     promouvoir
    0.48
     polis
    0.47
    פים
    0.47
    льнай
    0.46
     analyt
    0.46
    дных
    0.46
    Activations Density 0.002%

    No Known Activations