© 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. 34094
    Prev
    Next
    INDEX
    Explanations

    kingdom of God

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

    code and technical terms

    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
    ت
    0.47
     subsequ
    0.44
    ថ
    0.43
     distingu
    0.43
    望
    0.43
     intim
    0.43
    +
    0.42
     following
    0.42
    1
    0.42
     Following
    0.41
    POSITIVE LOGITS
    TrackAngle
    0.51
     приятно
    0.50
    Okno
    0.50
    йдз
    0.49
    Penumpang
    0.49
    ረጃ
    0.49
     slto
    0.47
     presenceData
    0.46
     সাম্প্র
    0.46
     окно
    0.46
    Activations Density 0.000%

    No Known Activations