© 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. 233781
    Prev
    Next
    INDEX
    Explanations

    reduces, precursor, minimum, continue

    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
     অন্যরা
    0.46
    "),],
    0.44
     competitors
    0.43
     του
    0.42
     IT
    0.41
     developers
    0.41
     airlines
    0.41
     others
    0.40
    ",
    0.40
     shaver
    0.40
    POSITIVE LOGITS
    لة
    0.53
     शारीरिक
    0.51
     dukkham
    0.48
    Ꮆ
    0.44
     Artículo
    0.44
     derogatory
    0.43
    跖
    0.43
    asign
    0.43
    inio
    0.42
     فونٹ
    0.42
    Activations Density 0.000%

    No Known Activations