© 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. 195352
    Prev
    Next
    INDEX
    Explanations

    honeymoon suite, CVE Publishing, Chinese Heaven

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

    potential future imports

    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
    ଝ
    0.48
    anso
    0.47
    ડી
    0.46
    Java
    0.46
    ーツ
    0.45
    امد
    0.44
    semblance
    0.44
    SMS
    0.44
    де
    0.44
    아
    0.44
    POSITIVE LOGITS
     Amtrak
    0.58
     potentiel
    0.47
     MCI
    0.47
     CII
    0.47
     environmental
    0.46
     ENVIRONMENTAL
    0.46
     lyophil
    0.46
     intégré
    0.46
     champignons
    0.46
     Canva
    0.45
    Activations Density 0.001%

    No Known Activations