© 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. 148638
    Prev
    Next
    INDEX
    Explanations

    capturing moments

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

    link

    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
    Section
    0.57
    h
    0.52
    Garage
    0.51
    Hashing
    0.50
    Expand
    0.49
    c
    0.47
    Hallo
    0.47
    Heb
    0.46
    With
    0.46
    Т
    0.46
    POSITIVE LOGITS
     singer
    0.52
     singers
    0.52
    ichi
    0.49
     diosa
    0.49
    ustom
    0.49
    ductors
    0.49
    uteurs
    0.49
     pinturas
    0.48
    ereo
    0.48
     oficinas
    0.48
    Activations Density 0.000%

    No Known Activations