© 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. 180792
    Prev
    Next
    INDEX
    Explanations

    FIRST time, September 30, club rides

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

    thickness capacity

    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
    i
    0.49
    ak
    0.47
    ints
    0.47
    H
    0.47
    il
    0.46
    hr
    0.46
     gerar
    0.46
    im
    0.46
    xi
    0.44
    y
    0.44
    POSITIVE LOGITS
    始终
    0.55
     अधिकांश
    0.51
     अक्सर
    0.49
    旄
    0.49
    प्ले
    0.48
    属性
    0.47
     తిరిగి
    0.47
    雩
    0.47
    􀂾
    0.47
    ப்பு
    0.46
    Activations Density 0.000%

    No Known Activations