© 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. 39454
    Prev
    Next
    INDEX
    Explanations

    state of being or availability

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

    things are configured or equipped

    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
    cantidad
    0.48
    hny
    0.47
    ienst
    0.45
    िएगा
    0.43
    illiant
    0.43
     अत्यंत
    0.42
     niềm
    0.41
     生
    0.41
    หว่าง
    0.41
    extracted
    0.41
    POSITIVE LOGITS
     operated
    0.68
     populated
    0.63
     inhabited
    0.60
     operates
    0.57
     outfitted
    0.57
    operated
    0.53
     staffed
    0.53
     capaces
    0.52
     operate
    0.52
     käyttää
    0.52
    Activations Density 0.141%

    No Known Activations