© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72009
    Prev
    Next
    INDEX
    Explanations

    locations and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     akhirnya
    -1.44
     случайно
    -1.41
    corrhi
    -1.38
    に行って
    -1.35
    providedIn
    -1.33
    に行った
    -1.32
     YOUR
    -1.31
    づけ
    -1.30
    んですよね
    -1.29
     ванной
    -1.29
    POSITIVE LOGITS
    が
    1.41
    を
    1.35
    ですが
    1.31
    で
    1.26
    や
    1.21
    から
    1.16
    は
    1.11
    それも
    1.08
    结语
    1.08
    などの
    1.08
    Activations Density 0.030%

    No Known Activations