© 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. 70224
    Prev
    Next
    INDEX
    Explanations

    form into balls. Roll

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

    social media, emotional connection, workshops

    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
    ぺ
    0.49
    ವಾಗಿ
    0.47
    калә
    0.46
     पाक
    0.45
    ఎ
    0.44
    Afrique
    0.44
     والا
    0.44
     ആൻ
    0.44
    𒀊
    0.43
     Zahlung
    0.43
    POSITIVE LOGITS
     shavings
    0.50
    t
    0.46
     dirigés
    0.44
    д
    0.42
    d
    0.42
    tur
    0.42
    riks
    0.41
     günd
    0.40
    ի
    0.39
    Rac
    0.39
    Activations Density 0.002%

    No Known Activations