© 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. 77050
    Prev
    Next
    INDEX
    Explanations

    numbers with four

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

    actions and communication

    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
    FORD
    0.53
    TOUR
    0.47
     காலம்
    0.44
    clas
    0.44
     inasmuch
    0.44
    RESS
    0.43
    ्स
    0.43
    츠
    0.42
    FORE
    0.42
     আভ
    0.41
    POSITIVE LOGITS
    er
    0.54
     =
    0.50
    liu
    0.45
    erina
    0.44
    ုပ်
    0.44
    ẵn
    0.43
    চর্
    0.43
     voldoende
    0.43
    ার্থক
    0.43
     possessions
    0.42
    Activations Density 0.000%

    No Known Activations