© 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. 179574
    Prev
    Next
    INDEX
    Explanations

    return to considerations

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

    press event, liked, included, </li>, ?

    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
     вся
    0.50
    荪
    0.47
     כל
    0.45
     എല്ലാം
    0.45
     усі
    0.44
     всички
    0.44
     എല്ലാ
    0.43
    ombrie
    0.43
     ті
    0.43
     sämt
    0.43
    POSITIVE LOGITS
    ۳
    0.48
     Offences
    0.45
    ਸ਼
    0.42
     ملین
    0.42
    টায়
    0.42
     contrario
    0.41
     своё
    0.41
    。
    0.41
    قتل
    0.41
    強い
    0.40
    Activations Density 0.000%

    No Known Activations