© 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. 160977
    Prev
    Next
    INDEX
    Explanations

    hotel and accommodation

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

    health and quality

    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
    akrishnan
    0.44
     TIMER
    0.44
    伊藤
    0.42
    誓
    0.42
     EEOC
    0.42
     rRNA
    0.41
    LETIN
    0.41
    ಕ್ಕ
    0.41
    ங்கா
    0.40
     MZ
    0.40
    POSITIVE LOGITS
     saúde
    0.56
     santé
    0.52
    🛌
    0.52
     chis
    0.51
    </td>
    0.50
     qualidade
    0.50
     qualités
    0.50
     health
    0.49
    health
    0.48
     qualità
    0.48
    Activations Density 0.000%

    No Known Activations