© 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. 22413
    Prev
    Next
    INDEX
    Explanations

    Goddess Saraswati, infinity stones

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

    descriptions of abstract concepts

    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
     are
    0.51
    ਤੇ
    0.50
    ্যের
    0.48
     प्रकट
    0.47
    때
    0.47
    워
    0.45
    are
    0.45
     प्रतिबद्ध
    0.44
    '
    0.44
    튼
    0.44
    POSITIVE LOGITS
     Cakes
    0.50
     Eigenschaften
    0.48
     Dienste
    0.44
     మొద
    0.44
    Callories
    0.44
     höchsten
    0.43
     首先
    0.43
     હંમે
    0.42
     চলুন
    0.42
    👩
    0.41
    Activations Density 0.000%

    No Known Activations