© 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. 245508
    Prev
    Next
    INDEX
    Explanations

    online casino promotions

    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
    制定
    0.38
    amo
    0.38
    entry
    0.37
    <0x0D>
    0.37
     itself
    0.37
     &=&
    0.37
    thar
    0.37
     ぐらい
    0.36
    hed
    0.36
    মোঃ
    0.36
    POSITIVE LOGITS
    Swe
    0.46
     ہیں۔
    0.43
    λευ
    0.43
    Bew
    0.42
    𝒸
    0.41
    Although
    0.41
     deği
    0.41
    ίνεται
    0.40
    ILERS
    0.39
     erfahren
    0.38
    Activations Density 0.000%

    No Known Activations