© 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. 16075
    Prev
    Next
    INDEX
    Explanations

    initiation or beginning

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

    descriptive elaboration

    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
     these
    0.44
     THESE
    0.38
     when
    0.38
     usar
    0.37
     (
    0.36
     usan
    0.36
     These
    0.35
     using
    0.35
     estas
    0.35
     estos
    0.34
    POSITIVE LOGITS
     довольно
    0.54
     상당히
    0.49
     αρκε
    0.45
     весьма
    0.44
     досить
    0.44
     khá
    0.43
    꽤
    0.42
     oldukça
    0.40
     বেশকিছু
    0.39
    非常的
    0.39
    Activations Density 0.030%

    No Known Activations