© 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. 23875
    Prev
    Next
    INDEX
    Explanations

    Addison Axminster

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

    technical keywords

    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
     ಐ
    0.44
     للد
    0.43
    ួន
    0.41
     maxim
    0.41
     रामबा
    0.40
     fles
    0.39
     toolkit
    0.39
    thebetter
    0.39
     wrest
    0.38
    菊
    0.38
    POSITIVE LOGITS
    MPT
    0.42
    iece
    0.40
    isah
    0.40
     arasında
    0.39
    yspace
    0.39
    旪
    0.39
    orak
    0.38
    ipkan
    0.38
    dington
    0.38
    ameva
    0.38
    Activations Density 0.000%

    No Known Activations