© 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. 150585
    Prev
    Next
    INDEX
    Explanations

    importance of services

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

    describing specific things and sounds

    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
     o
    0.60
     l
    0.59
     информация
    0.53
     Swiss
    0.51
     Professor
    0.51
     v
    0.50
     s
    0.49
     More
    0.48
     continues
    0.48
     Lancet
    0.48
    POSITIVE LOGITS
    パッド
    0.53
    pads
    0.51
     ቦ
    0.50
     ఇటీ
    0.47
     applicator
    0.47
    ballage
    0.47
     успі
    0.47
     adhipp
    0.46
     adher
    0.45
     ಕೆಲವು
    0.45
    Activations Density 0.001%

    No Known Activations