© 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. 58469
    Prev
    Next
    INDEX
    Explanations

    spelled backwards

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

    centering, notify Inspector, values, even overwhelm

    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
    悽
    0.53
     Fingers
    0.48
    VH
    0.44
     Komfort
    0.44
     Kreat
    0.44
     Förderung
    0.44
    ια
    0.43
    IR
    0.43
     Fokus
    0.43
     Materi
    0.43
    POSITIVE LOGITS
    َل
    0.48
    ويل
    0.48
     trent
    0.46
     പി
    0.45
     و
    0.42
     spite
    0.41
    Airport
    0.41
    وال
    0.41
     pigment
    0.40
    营业
    0.40
    Activations Density 0.001%

    No Known Activations