© 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-16K
    7. 12821
    Prev
    Next
    INDEX
    Explanations

    to compile, to administer

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

    legal consequences or basis

    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_16k_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
     hickory
    0.50
     ordinarily
    0.49
     بواسط
    0.48
     ଗ
    0.48
     meritorious
    0.48
     入っ
    0.48
    <unused656>
    0.45
     entryway
    0.45
     নিখ
    0.44
     ､
    0.44
    POSITIVE LOGITS
    <start_of_image>
    0.44
    ager
    0.43
    هش
    0.43
    ends
    0.42
    Intermediate
    0.42
    asks
    0.42
     РФ
    0.41
     kurz
    0.41
    ubation
    0.41
     ends
    0.40
    Activations Density 0.002%

    No Known Activations