© 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. 151930
    Prev
    Next
    INDEX
    Explanations

    from matches to work

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

    reward, copy, ranking, staged

    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
    ᔾ
    0.55
    ᖓ
    0.50
     Makeup
    0.50
    inizi
    0.49
     കൂടുതല്‍
    0.48
     habitudes
    0.48
    šanas
    0.47
    丏
    0.47
     Boogie
    0.47
     ദു
    0.46
    POSITIVE LOGITS
     spouses
    0.44
     obtained
    0.44
     timely
    0.43
     gend
    0.43
     coincides
    0.42
    thesis
    0.41
     untested
    0.41
     distilled
    0.40
     syll
    0.40
     unbound
    0.39
    Activations Density 0.000%

    No Known Activations