© 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. 221549
    Prev
    Next
    INDEX
    Explanations

    likelihood that

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

    destination and travel planning

    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
     finans
    0.49
    Twitter
    0.48
     Twitter
    0.46
    ```
    0.45
    ান্তরে
    0.44
    ${
    0.43
     দৌ
    0.42
     puj
    0.42
     prowess
    0.41
     वित्त
    0.41
    POSITIVE LOGITS
     लेक्चर
    0.45
    ޔ
    0.43
    িন্দু
    0.43
    ۹
    0.43
    राव
    0.42
     Рус
    0.42
     Großbritannien
    0.42
     Eros
    0.41
    𒊬
    0.41
     جشنواره
    0.41
    Activations Density 0.001%

    No Known Activations