© 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. 68272
    Prev
    Next
    INDEX
    Explanations

    and so on

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

    listing examples and options

    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
     و
    0.76
     व
    0.66
     ও
    0.65
    ແລະ
    0.63
     ו
    0.59
     आणि
    0.55
     Gottlieb
    0.53
     druge
    0.52
     Communion
    0.51
     Bücher
    0.51
    POSITIVE LOGITS
    a
    0.83
    q
    0.68
    on
    0.67
    வற்றை
    0.64
    ה
    0.62
    etera
    0.61
    j
    0.60
    ли
    0.59
    ре
    0.58
     in
    0.56
    Activations Density 0.026%

    No Known Activations