© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 98865
    Prev
    Next
    INDEX
    Explanations

    med Bo chevron polished exact mobile queen

    np_acts-logits-general · gemini-2.5-flash-lite

    surgeons, jobs, data, see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     이러한
    0.51
    ᗜ
    0.49
     assumptive
    0.49
    otically
    0.48
    Primitive
    0.47
    theoretic
    0.46
    uscular
    0.45
    嚢
    0.45
     இந்தப்
    0.45
    inguistic
    0.43
    POSITIVE LOGITS
     einzigen
    0.48
     pokoj
    0.48
    s
    0.48
    meh
    0.47
    t
    0.47
     died
    0.47
     repaired
    0.47
     repairing
    0.46
    m
    0.46
     voted
    0.46
    Activations Density 0.002%

    No Known Activations