© 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. 194560
    Prev
    Next
    INDEX
    Explanations

    comparison or distinction

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

    when discussing drawbacks

    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
    નિ
    0.50
    Фа
    0.48
     FAT
    0.45
    Ги
    0.44
    사실
    0.44
     Magistrates
    0.43
    엄
    0.42
     magistrates
    0.41
     Parisi
    0.41
     Robust
    0.41
    POSITIVE LOGITS
    ucceeded
    0.52
     ")";
    0.52
     prêts
    0.47
    ickness
    0.46
     戦
    0.46
     ประมาณ
    0.45
     aircraft
    0.44
     drugs
    0.43
     বায়ু
    0.43
    ষুধ
    0.43
    Activations Density 0.001%

    No Known Activations