© 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. 126417
    Prev
    Next
    INDEX
    Explanations

    ready for delivery

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

    resolves temporary glitches

    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
    刷
    0.46
     они
    0.44
    coid
    0.43
    ังหวัด
    0.41
    群
    0.41
     вони
    0.41
    ыл
    0.40
    Universidad
    0.40
    公司
    0.40
     ομάδα
    0.40
    POSITIVE LOGITS
     infamous
    0.49
     தக
    0.44
     বক্তব্যের
    0.43
     பாரம்பரிய
    0.42
     কথাই
    0.40
    rières
    0.40
     notorious
    0.40
     कामका
    0.40
     மாட்ட
    0.39
    觊
    0.39
    Activations Density 0.000%

    No Known Activations