© 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. 45298
    Prev
    Next
    INDEX
    Explanations

    company address and contact

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

    what happened

    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
     పరీక్ష
    0.49
    缀
    0.44
    Inspection
    0.43
     SEEK
    0.42
     Accessory
    0.42
    ၿ
    0.41
    बॉ
    0.41
    ুজ
    0.40
     PLUS
    0.40
    Betty
    0.40
    POSITIVE LOGITS
     relegated
    0.50
     raya
    0.46
     subordinated
    0.45
    radas
    0.44
     monopol
    0.43
     rade
    0.42
    zmdi
    0.42
     jod
    0.42
     marvell
    0.42
     scandalous
    0.42
    Activations Density 0.000%

    No Known Activations