© 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. 237906
    Prev
    Next
    INDEX
    Explanations

    done automatically

    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
    objeto
    0.50
     …………
    0.50
     گے۔
    0.49
     வேறு
    0.48
     ……..
    0.48
    osas
    0.47
    وبات
    0.47
    ۲
    0.47
    ㄺ
    0.47
     های
    0.46
    POSITIVE LOGITS
     Oni
    0.43
     ous
    0.42
    的女
    0.41
     Kommunikation
    0.41
     Sne
    0.41
    亟
    0.41
     upon
    0.41
     angrily
    0.40
    liche
    0.40
     js
    0.39
    Activations Density 0.000%

    No Known Activations