© 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. 52846
    Prev
    Next
    INDEX
    Explanations

    latest developments, convertible debt

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

    AI, assume, different, combination

    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
     ис
    0.49
     Bread
    0.45
    ↵↵
    0.43
     (
    0.41
     landfall
    0.41
     T
    0.41
    อัต
    0.40
    <eos>
    0.40
     macro
    0.40
     C
    0.40
    POSITIVE LOGITS
     acquistare
    0.57
    𝐝
    0.53
    𝒂
    0.52
     अमा
    0.52
     başlad
    0.51
     خریداری
    0.51
     necesitamos
    0.50
    烪
    0.50
     jaką
    0.49
    <unused51>
    0.49
    Activations Density 0.000%

    No Known Activations