© 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. 204864
    Prev
    Next
    INDEX
    Explanations

    right to

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

    building descriptive phrases

    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
     বান
    0.49
    tao
    0.49
     generator
    0.49
     modificare
    0.49
    ~~~~~~~~~~~~~~~~
    0.48
    ভির
    0.47
    ~!
    0.47
    producer
    0.47
    łaś
    0.47
     últ
    0.46
    POSITIVE LOGITS
    細かい
    0.44
    тический
    0.42
     medi
    0.42
    胭脂
    0.41
    痛み
    0.41
    框
    0.41
    ブロック
    0.40
     Bloc
    0.40
    抖音
    0.40
    サンプル
    0.39
    Activations Density 0.001%

    No Known Activations