© 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. 33371
    Prev
    Next
    INDEX
    Explanations

    /profile/

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

    URLs with slashes

    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
    Acetoxy
    0.42
    ภู
    0.40
    ﾌ
    0.40
    IVA
    0.39
    대가
    0.39
    েন্দ্রলাল
    0.38
     этого
    0.38
    ຣ
    0.38
     этих
    0.37
    沼
    0.37
    POSITIVE LOGITS
    more
    0.41
    orcid
    0.41
    ôme
    0.39
     kanssa
    0.38
    是真的
    0.38
    aking
    0.38
     ಎಂದು
    0.38
    ute
    0.38
    一樣
    0.38
     Weir
    0.38
    Activations Density 0.005%

    No Known Activations