© 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. 51481
    Prev
    Next
    INDEX
    Explanations

    numbers, MIT events, corrupting, range, down key

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

    Mathematical expressions and 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
     habido
    0.49
     engender
    0.48
     derog
    0.46
     impairs
    0.45
     օ
    0.45
     manquer
    0.44
     sezonie
    0.43
     kock
    0.43
     contiene
    0.42
     dracon
    0.42
    POSITIVE LOGITS
    4
    0.53
    5
    0.52
    FON
    0.48
    वू
    0.46
    Pixmap
    0.46
    6
    0.46
    織
    0.46
    NO
    0.45
    Recorder
    0.44
     ভেঙ্গে
    0.44
    Activations Density 0.000%

    No Known Activations