© 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. 87972
    Prev
    Next
    INDEX
    Explanations

    entry was posted

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

    here's a breakdown why

    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
    า
    0.48
    MARKS
    0.48
    MEDI
    0.48
    }_{-
    0.47
    SJ
    0.47
    SSON
    0.46
     innovations
    0.46
    ಲ್ಲು
    0.45
    др
    0.45
     beans
    0.45
    POSITIVE LOGITS
     https
    0.45
    ​​​​
    0.44
     বাল
    0.44
     attén
    0.43
    ﮔ
    0.43
     প্রচার
    0.43
    蓋
    0.43
    around
    0.43
    <0x83>
    0.42
     আছি
    0.42
    Activations Density 0.000%

    No Known Activations