© 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. 88665
    Prev
    Next
    INDEX
    Explanations

    free or faults

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

    technical screen

    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
    из
    0.51
    SSSS
    0.43
    іб
    0.43
    融入
    0.43
    std
    0.42
    ри
    0.42
    BEGIN
    0.42
    盏
    0.42
    стана
    0.42
    ेर
    0.41
    POSITIVE LOGITS
     attenuate
    0.53
     iteratively
    0.52
     outliers
    0.52
     ambigu
    0.51
     troubleshoot
    0.50
     informally
    0.50
     abate
    0.50
     privately
    0.49
     dezvolt
    0.49
     explicitly
    0.49
    Activations Density 0.000%

    No Known Activations