© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5577
    Prev
    Next
    INDEX
    Explanations

    physical science and earth concepts

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

    water droplets molecules cells

    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_53_width_65k_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
    讲述
    0.53
     Verbal
    0.48
     thuyết
    0.48
     కథ
    0.48
     textual
    0.46
    藪
    0.45
     berätt
    0.45
    演绎
    0.44
    讲
    0.44
     ascertaining
    0.44
    POSITIVE LOGITS
     passes
    0.43
    の中に
    0.41
    Earth
    0.38
     প্রাণের
    0.38
     cpu
    0.37
    キャンセル
    0.37
     messed
    0.37
    それぞれの
    0.37
     molecules
    0.36
     molecule
    0.36
    Activations Density 0.000%

    No Known Activations