© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 1162
    Prev
    Next
    INDEX
    Explanations

    general terms for people

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

    identifying who or what

    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
     ஆகியவை
    0.25
    }$.
    0.25
     ซึ่ง
    0.25
     删除
    0.25
    Об
    0.22
     端
    0.22
    တစ်ခု
    0.22
     அனைத்தும்
    0.22
    แต่ละ
    0.21
    。
    0.21
    POSITIVE LOGITS
     who
    0.30
    who
    0.27
     ktorí
    0.27
    คนที่
    0.25
    한테
    0.25
     кто
    0.24
     хто
    0.24
     quien
    0.23
     যারা
    0.23
     народу
    0.21
    Activations Density 0.479%

    No Known Activations