© 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. 125881
    Prev
    Next
    INDEX
    Explanations

    9:30 PM

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

    topic introductions

    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
    DrvGPIO
    0.63
     jogador
    0.57
     argentino
    0.56
    
    0.55
     indiquer
    0.54
     alguns
    0.54
     accél
    0.53
    TakePhoto
    0.53
     fini
    0.53
    ڎ
    0.53
    POSITIVE LOGITS
    klore
    0.41
     Men
    0.41
    acs
    0.40
     Fisheries
    0.40
     Arte
    0.40
    \
    0.39
    Pot
    0.39
     Mixture
    0.39
     Consensus
    0.38
     Kunst
    0.38
    Activations Density 0.000%

    No Known Activations