© 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. 61409
    Prev
    Next
    INDEX
    Explanations

    the word after common words

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

    anticholinergic burden hypogonadism paraphilia

    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
     lawfully
    0.60
     water
    0.53
     and
    0.47
     legally
    0.46
     melaksanakan
    0.46
     soda
    0.46
     Z
    0.45
     web
    0.45
     Armor
    0.45
     B
    0.45
    POSITIVE LOGITS
    映画
    0.57
    тың
    0.52
    的世界
    0.50
    に関する
    0.49
     eloqu
    0.48
    ༦
    0.47
    ܸ
    0.47
     तारीफ
    0.47
    🤓
    0.47
    𝗆
    0.47
    Activations Density 0.000%

    No Known Activations