© 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. 173066
    Prev
    Next
    INDEX
    Explanations

    maxim or MAXIMUM

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

    animals and people

    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
    <unused65>
    0.46
    <unused33>
    0.46
     пье
    0.43
    θέ
    0.43
     сайті
    0.42
     خرید
    0.41
    课
    0.41
    Dijstra
    0.40
    чего
    0.40
    Ꭰ
    0.40
    POSITIVE LOGITS
     lifespan
    0.49
     multiv
    0.48
     maksimum
    0.47
     maxim
    0.46
     korišten
    0.45
     hardy
    0.44
    хран
    0.44
     noten
    0.43
    ₁+
    0.43
     MAXIMUM
    0.43
    Activations Density 0.000%

    No Known Activations