© 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. 203519
    Prev
    Next
    INDEX
    Explanations

    enables a, to me, as men, and tagline, while browsing

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

    what do you call

    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
    ر
    0.54
    研究
    0.52
    ר
    0.52
    かけて
    0.50
    ה
    0.50
    燗
    0.49
    ጇ
    0.48
     infección
    0.48
     récent
    0.48
    ل
    0.48
    POSITIVE LOGITS
     IntPtr
    0.44
     SME
    0.44
    <unused442>
    0.43
    shan
    0.43
     mush
    0.42
     churn
    0.42
     Mash
    0.41
    attho
    0.41
     SMEs
    0.41
     subordinate
    0.40
    Activations Density 0.003%

    No Known Activations