© 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. 201839
    Prev
    Next
    INDEX
    Explanations

    contact, membership, oil, listen

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

    common or simple following unusual

    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
    ್ಯಾ
    0.47
    alignParentRight
    0.40
     AdapterView
    0.40
    PagerAdapter
    0.40
    lastIndexOf
    0.38
     '['
    0.38
    য়া
    0.38
    新品
    0.38
    .([]
    0.38
     Remarks
    0.38
    POSITIVE LOGITS
     tranquille
    0.46
    ļ
    0.46
     commotion
    0.45
     bruto
    0.44
     كي
    0.43
     szükséges
    0.43
     şeyler
    0.42
     ön
    0.42
     stupidity
    0.42
     servitude
    0.42
    Activations Density 0.000%

    No Known Activations