© 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. 60272
    Prev
    Next
    INDEX
    Explanations

    directory of officials or bloggers

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

    time, coordinates, methanol, infinitely

    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
     alternatively
    0.48
     includes
    0.45
     recovers
    0.44
     forfe
    0.44
    꼰
    0.43
    мак
    0.42
     severity
    0.42
     milder
    0.41
     $"
    0.41
    ინა
    0.40
    POSITIVE LOGITS
     מו
    0.47
     பேரா
    0.46
    更换
    0.46
     טי
    0.45
     नींव
    0.45
     מס
    0.44
     जीने
    0.44
     स्पी
    0.44
     muut
    0.43
     일어나
    0.43
    Activations Density 0.000%

    No Known Activations