© 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. 96390
    Prev
    Next
    INDEX
    Explanations

    adjective/adverb noun/verb collocations

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

    anonymous blind model comparison

    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
    waan
    0.42
     AY
    0.41
    }_{+
    0.40
    ាំ
    0.40
    ought
    0.39
    二是
    0.39
    RY
    0.39
    ７
    0.39
    mares
    0.38
     IA
    0.37
    POSITIVE LOGITS
     గేమ్
    0.50
    渲
    0.49
     strutture
    0.48
    榫
    0.45
     شهری
    0.45
     δημιουργ
    0.44
    😲
    0.44
     प्रोजेक्ट
    0.43
    侪
    0.43
    ören
    0.43
    Activations Density 0.001%

    No Known Activations