© 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. 68306
    Prev
    Next
    INDEX
    Explanations

    called our, importantly is, Cookies if, month trial, change based, female students, savings each

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

    time for items to dry

    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
     extrac
    0.50
     district
    0.46
     super
    0.46
    だったら
    0.46
     THEM
    0.44
     them
    0.44
    <0xE2>
    0.44
     SUPER
    0.43
     nossa
    0.42
     Super
    0.42
    POSITIVE LOGITS
    समाचार
    0.50
    鲽
    0.47
     सदस्यों
    0.46
    नहीं
    0.46
    electrons
    0.46
    鰱
    0.46
    abdomen
    0.45
     सब्ज
    0.44
    lès
    0.44
    ruct
    0.43
    Activations Density 0.001%

    No Known Activations