© 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. 107327
    Prev
    Next
    INDEX
    Explanations

    need to help

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

    harmful effects

    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
    Interval
    0.51
    看
    0.47
    ENE
    0.47
    Going
    0.46
    Influence
    0.45
    Beacon
    0.44
    аль
    0.44
    nW
    0.44
    They
    0.43
    Es
    0.43
    POSITIVE LOGITS
    cropped
    0.46
     lớp
    0.43
     agrícola
    0.43
     ঘটে
    0.43
     ધો
    0.43
     slecht
    0.43
    恹
    0.42
    োল
    0.42
     শিক্ষার
    0.42
     preponder
    0.42
    Activations Density 0.000%

    No Known Activations