© 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. 221765
    Prev
    Next
    INDEX
    Explanations

    when it was not

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

    choppy sentences

    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
    वण्यात
    0.47
    esinde
    0.45
     एफ
    0.43
    з
    0.42
    वणे
    0.42
     mortals
    0.42
     meditations
    0.42
    လုံး
    0.42
    琉
    0.42
    荏
    0.42
    POSITIVE LOGITS
    。
    0.49
    ।
    0.45
     sConfig
    0.42
    LET
    0.42
     tengan
    0.40
     smoker
    0.40
     Sphere
    0.40
    SupportActionBar
    0.40
     sinar
    0.40
    问题
    0.40
    Activations Density 0.001%

    No Known Activations