© 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. 208698
    Prev
    Next
    INDEX
    Explanations

    or encourage

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

    # and *

    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
    ährt
    0.52
    𝒓
    0.47
    ICKET
    0.47
     všech
    0.46
     પ્રેમ
    0.46
     thuyền
    0.46
     jamás
    0.45
    𝐎
    0.45
    ｵ
    0.45
    IGNED
    0.45
    POSITIVE LOGITS
     probate
    0.44
     fragmentation
    0.43
    ieht
    0.42
     urgency
    0.42
     Reconstruction
    0.42
     potency
    0.42
     reconstruction
    0.41
    ported
    0.41
     critical
    0.41
     ::
    0.41
    Activations Density 0.000%

    No Known Activations