© 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. 73909
    Prev
    Next
    INDEX
    Explanations

    followed by related terms

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

    ultime, still, brave

    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
    lo
    0.52
    {
    0.51
    к
    0.49
    estly
    0.47
    ndef
    0.47
    justify
    0.47
    ю
    0.46
    ust
    0.45
    ،
    0.45
    ند
    0.44
    POSITIVE LOGITS
     importing
    0.53
     fluency
    0.51
     fornisce
    0.51
     highlighter
    0.50
     horsepower
    0.49
     powerAll
    0.49
     esercizi
    0.49
     flue
    0.48
     secondNumber
    0.48
     complications
    0.48
    Activations Density 0.001%

    No Known Activations