© 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. 222777
    Prev
    Next
    INDEX
    Explanations

    business and science terms

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

    provide text to analyze

    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
     underwent
    0.54
    ‘
    0.52
    inheritdoc
    0.48
    Screenshot
    0.46
    ʼ
    0.45
    Users
    0.44
     усіх
    0.44
     органів
    0.44
     χρή
    0.43
    車の
    0.43
    POSITIVE LOGITS
     barbecue
    0.49
     BBQ
    0.45
     \""
    0.43
     soil
    0.43
     Polaroid
    0.43
    KE
    0.42
     blå
    0.42
    ਠ
    0.42
    뀜
    0.42
     aloe
    0.42
    Activations Density 0.001%

    No Known Activations