© 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. 1794
    Prev
    Next
    INDEX
    Explanations

    questions about topics

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

    asking what about plans and data

    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
     جیسے
    0.45
    ۔
    0.43
     کیونکہ
    0.43
     மட்டுமல்ல
    0.42
     بدء
    0.42
    非常
    0.42
    ルの
    0.41
    所の
    0.38
    الد
    0.38
    ।
    0.38
    POSITIVE LOGITS
     underlies
    0.64
     we
    0.63
     you
    0.61
    soever
    0.60
     youre
    0.55
    ങ്ങളാണ്
    0.53
    ？”
    0.52
     they
    0.52
     would
    0.52
     você
    0.52
    Activations Density 0.141%

    No Known Activations