© 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. 240752
    Prev
    Next
    INDEX
    Explanations

    every kind of

    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
     debate
    0.48
    主要是
    0.45
    드는
    0.45
    为
    0.44
     mainly
    0.44
     finite
    0.42
     (‘
    0.42
     임
    0.41
     Wyndham
    0.41
     する
    0.41
    POSITIVE LOGITS
     ऑटो
    0.54
    ഐ
    0.50
     pés
    0.48
    រយៈពេល
    0.48
     voila
    0.47
    serde
    0.47
     envía
    0.47
     Unterstüt
    0.47
    ühr
    0.47
     unterstützen
    0.47
    Activations Density 0.003%

    No Known Activations