© 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. 168999
    Prev
    Next
    INDEX
    Explanations

    to any allowed purchase

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

    variations, direct, challenging

    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
    iej
    0.51
    йга
    0.47
    िव
    0.46
    ват
    0.46
    HALF
    0.45
    इंद
    0.45
    izou
    0.44
    ق
    0.44
    ца
    0.43
    нии
    0.43
    POSITIVE LOGITS
     थेट
    0.54
     కర్
    0.53
     然而
    0.50
     पहा
    0.50
     మరియు
    0.49
    yness
    0.48
     chronicle
    0.48
    Downloaded
    0.48
    谚
    0.48
     सुमारे
    0.47
    Activations Density 0.001%

    No Known Activations