© 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. 69047
    Prev
    Next
    INDEX
    Explanations

    services, own, current, turf

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

    lack of specific instances

    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
    꽤
    0.45
     volna
    0.43
     고려
    0.41
     рассматри
    0.41
    榉
    0.40
    packageName
    0.40
     consola
    0.40
    getPackageName
    0.39
     рассмотре
    0.39
    팸
    0.38
    POSITIVE LOGITS
     کرکے
    0.51
    ن
    0.47
     células
    0.46
     세포
    0.46
     dx
    0.44
    cells
    0.44
     immortality
    0.44
     आणि
    0.44
     انها
    0.43
     cells
    0.43
    Activations Density 0.001%

    No Known Activations