© 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. 156648
    Prev
    Next
    INDEX
    Explanations

    booked by

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

    average dimension calculation

    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
    tenberg
    0.49
     गिलास
    0.49
    τηση
    0.46
    ตรง
    0.45
    reathe
    0.44
    จัย
    0.43
     गैर
    0.43
    🎳
    0.43
    keeping
    0.42
    Ꮥ
    0.41
    POSITIVE LOGITS
    ınd
    0.50
    ૂર
    0.47
     drücken
    0.46
     diffusione
    0.45
    ానిక
    0.44
    نية
    0.43
     coolant
    0.43
    öre
    0.43
    appy
    0.42
     Qin
    0.42
    Activations Density 0.000%

    No Known Activations