© 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. 158508
    Prev
    Next
    INDEX
    Explanations

    platform, fine, down south, more

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

    nftables keyword

    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
     vostra
    0.52
     लेट्स
    0.52
     agacch
    0.51
    gunaan
    0.50
     illustrazione
    0.49
    FileInputExcel
    0.49
    )‏
    0.49
    WithFieldContext
    0.49
    ♍
    0.48
     গ্রন্থে
    0.48
    POSITIVE LOGITS
    لي
    0.47
    োর
    0.44
    ช่วง
    0.43
    тири
    0.42
     Mathews
    0.40
    缔
    0.40
    ാരണ
    0.39
        
    0.39
    ềm
    0.39
    ตำบล
    0.38
    Activations Density 0.000%

    No Known Activations