© 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. 181380
    Prev
    Next
    INDEX
    Explanations

    entities and their descriptors

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

    riddles and logical contradictions

    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
    Ripe
    0.44
    镣
    0.42
     inactivity
    0.42
     Ian
    0.41
     تاس
    0.41
    UIntValue
    0.40
    untas
    0.40
     Colin
    0.40
    谅
    0.40
    ريكا
    0.39
    POSITIVE LOGITS
     интересных
    0.51
     स्वयं
    0.49
     எல்லா
    0.48
     खेळ
    0.48
    ventana
    0.48
     दिलेल्या
    0.47
     ਲਈ
    0.47
     அறிவியல்
    0.46
     ಎಂಬ
    0.46
     डिवाइड
    0.46
    Activations Density 0.000%

    No Known Activations