© 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. 227251
    Prev
    Next
    INDEX
    Explanations

    able to or good for

    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
     PSF
    0.51
    d
    0.51
     Knight
    0.48
    pra
    0.48
    prop
    0.46
     Theatre
    0.46
     d
    0.46
    c
    0.46
     TV
    0.45
    Knight
    0.45
    POSITIVE LOGITS
     aumenta
    0.54
     понравилось
    0.50
     zwei
    0.49
     olması
    0.49
     erhöhen
    0.48
     ekonom
    0.47
     регули
    0.47
    某些
    0.47
     некоторых
    0.47
     табли
    0.47
    Activations Density 0.000%

    No Known Activations