© 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. 227608
    Prev
    Next
    INDEX
    Explanations

    web,

    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
    *
    0.45
     reducing
    0.44
     subtly
    0.44
     verbessern
    0.43
    行动
    0.43
     clearer
    0.42
     Sweeney
    0.42
    ("#{
    0.42
     mitigating
    0.41
     melhorar
    0.41
    POSITIVE LOGITS
    καν
    0.49
    лось
    0.49
    clients
    0.49
     ತಾ
    0.48
    𝘀
    0.48
     Dated
    0.46
    徊
    0.46
    𝗹
    0.46
     オリ
    0.45
    𝗳
    0.45
    Activations Density 0.002%

    No Known Activations