© 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. 7887
    Prev
    Next
    INDEX
    Explanations

    given parameters or inputs

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

    integers, strings, and array manipulation

    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
    avacanam
    0.43
    ἧ
    0.40
    showroom
    0.40
     fortiter
    0.39
     appellee
    0.38
    <unused67>
    0.37
     souh
    0.37
    embry
    0.37
    हून
    0.36
    酈
    0.36
    POSITIVE LOGITS
    字符串
    0.53
    任意
    0.45
     combinatorial
    0.45
     integers
    0.44
    给定
    0.44
     JavaScript
    0.44
    存储
    0.44
     randomly
    0.43
     Python
    0.43
     monotonically
    0.43
    Activations Density 0.002%

    No Known Activations