© 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. 21448
    Prev
    Next
    INDEX
    Explanations

    Read More

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

    list item 2

    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
    ა
    0.49
    ী
    0.48
    ឪ
    0.47
     оте
    0.45
    哆
    0.45
    ı
    0.44
     ""`
    0.43
    bere
    0.43
    那里
    0.43
    दया
    0.42
    POSITIVE LOGITS
     상
    0.43
     unpublished
    0.41
     پرس
    0.41
    ၞ
    0.41
    வின்
    0.41
    YA
    0.40
    Es
    0.40
     sued
    0.40
     restant
    0.40
     chevron
    0.40
    Activations Density 0.000%

    No Known Activations