© 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. 58896
    Prev
    Next
    INDEX
    Explanations

    until case

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

    sections, data, messages

    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
     masses
    0.52
     sages
    0.52
     evaluation
    0.51
    شی
    0.48
    Evaluation
    0.48
    ﺀ
    0.48
     );
    0.47
     resumes
    0.47
    ESS
    0.46
     .
    0.46
    POSITIVE LOGITS
    âtre
    0.52
    phenoxymethyl
    0.48
    érin
    0.48
    áme
    0.47
     McPherson
    0.47
    ífer
    0.47
    분에
    0.46
    بيه
    0.46
     capitán
    0.46
     восем
    0.46
    Activations Density 0.000%

    No Known Activations