© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10943
    Prev
    Next
    INDEX
    Explanations

    code comments and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    ணா
    2.63
    슨
    2.51
    an
    2.32
     forced
    2.25
     domestic
    2.19
    is
    2.18
    ﻦ
    2.14
    년대
    2.12
     рад
    2.10
    ими
    2.09
    POSITIVE LOGITS
     Tanto
    3.13
    yside
    2.93
    tanto
    2.82
    కీయ
    2.63
    tions
    2.59
    น์
    2.58
    tend
    2.58
     Immunohist
    2.56
    黜
    2.49
    ikation
    2.48
    Activations Density 0.018%

    No Known Activations