© 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. 176022
    Prev
    Next
    INDEX
    Explanations

    subjects to

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

    explaining differences or examples

    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
    ()!=
    0.49
     書い
    0.49
     जहाँ
    0.48
     Finishing
    0.48
     Adaptation
    0.46
    コク
    0.46
     Anything
    0.45
     никакого
    0.45
    ()==
    0.45
     IgG
    0.44
    POSITIVE LOGITS
     funding
    0.48
    ça
    0.46
    寻
    0.45
    пети
    0.44
     rapporte
    0.43
    Funding
    0.42
    实际
    0.41
     poset
    0.41
    दया
    0.41
    萦
    0.41
    Activations Density 0.001%

    No Known Activations