© 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. 172891
    Prev
    Next
    INDEX
    Explanations

    autobiographical meditation

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

    drink plenty of water

    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
     rainy
    0.46
    }\\
    0.45
     ל
    0.45
     day
    0.44
     kelompok
    0.44
    }$.
    0.43
     Ekonom
    0.43
     Dương
    0.43
    이는
    0.43
     '':
    0.43
    POSITIVE LOGITS
    раздо
    0.52
    굉
    0.50
     гораздо
    0.49
     урна
    0.48
    пру
    0.45
    Finland
    0.44
     posse
    0.44
    ramed
    0.43
     многи
    0.43
    喝酒
    0.42
    Activations Density 0.000%

    No Known Activations