© 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. 127198
    Prev
    Next
    INDEX
    Explanations

    video tutorial, highest peak, powerful illusion

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

    policy explanations

    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
     descansar
    0.45
     semuanya
    0.43
     tacos
    0.43
    ']},
    0.42
     nausea
    0.42
    それぞれ
    0.42
    nfasis
    0.41
     descanso
    0.41
     pamoja
    0.41
     compassion
    0.40
    POSITIVE LOGITS
    ياز
    0.49
     пове
    0.45
     नींव
    0.45
    TargetPath
    0.44
    ANTI
    0.44
    枌
    0.44
    怸
    0.43
     संस्थापक
    0.43
     нес
    0.43
     Ат
    0.43
    Activations Density 0.001%

    No Known Activations