© 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. 217190
    Prev
    Next
    INDEX
    Explanations

    gossip and net stuff

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

    cautious if supplies

    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
    JobList
    0.45
    pri
    0.45
     Requirement
    0.45
    list
    0.44
    pix
    0.43
    ibilit
    0.42
    visory
    0.41
    ｎ
    0.41
    osyl
    0.40
    穎
    0.40
    POSITIVE LOGITS
     segala
    0.51
     gigantes
    0.50
     руках
    0.50
     ederim
    0.48
    ज़
    0.48
     sebuah
    0.48
     gunung
    0.48
    HHHH
    0.47
     exceedingly
    0.46
     acide
    0.46
    Activations Density 0.005%

    No Known Activations