© 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. 51701
    Prev
    Next
    INDEX
    Explanations

    goals and resources

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

    Conversion rate calculations

    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
    س
    0.74
    ما
    0.59
     نقاط
    0.54
    ت
    0.54
    ون
    0.49
     شم
    0.48
    коли
    0.48
     در
    0.47
    き
    0.47
    بر
    0.46
    POSITIVE LOGITS
     reorgan
    0.61
     blogging
    0.49
     mineral
    0.48
     adjoining
    0.48
     reopening
    0.47
     resuming
    0.46
     Mineral
    0.45
     freehold
    0.45
     renormal
    0.45
     rearrange
    0.44
    Activations Density 0.000%

    No Known Activations