© 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. 42992
    Prev
    Next
    INDEX
    Explanations

    amounts to $

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

    weighing pros and cons

    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
     ultrasound
    0.42
     japonesa
    0.42
     tubular
    0.42
    唱
    0.42
    ಾನ್
    0.41
     ultrason
    0.40
     конструкция
    0.40
     package
    0.40
     pacote
    0.39
    ᵀ
    0.39
    POSITIVE LOGITS
    轫
    0.45
    ن
    0.41
    shifts
    0.40
    ق
    0.40
    খানেই
    0.40
     شک
    0.39
    MiddleCenter
    0.39
     indiquée
    0.39
    饥
    0.39
    nThe
    0.39
    Activations Density 0.000%

    No Known Activations