© 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. 237295
    Prev
    Next
    INDEX
    Explanations

    common phrases starting

    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
    केश
    0.46
    ToOne
    0.43
    年の
    0.43
     Vertreter
    0.43
     Maret
    0.42
    번
    0.42
     skinned
    0.41
    ้ย
    0.41
    鼈
    0.41
    സ്ത്ര
    0.40
    POSITIVE LOGITS
    チール
    0.47
     obliter
    0.46
     campgrounds
    0.43
     employability
    0.42
     simulators
    0.40
     engra
    0.40
    ステン
    0.39
     equestrian
    0.39
     یہی
    0.39
    为止
    0.39
    Activations Density 0.000%

    No Known Activations