© 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. 134967
    Prev
    Next
    INDEX
    Explanations

    Funds, Failure, restoration method

    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
    écution
    0.49
    轨道
    0.42
     стихо
    0.42
    ScienceStudent
    0.41
    ။
    0.41
    ่าว
    0.40
    锆
    0.40
     rôle
    0.39
     ад
    0.39
     troisième
    0.39
    POSITIVE LOGITS
     _____________
    0.40
    的一种
    0.40
     ________
    0.39
     but
    0.39
    total
    0.39
     ome
    0.39
    ____
    0.38
    だけでなく
    0.38
     defined
    0.37
    cost
    0.37
    Activations Density 0.216%

    No Known Activations