© 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. 69075
    Prev
    Next
    INDEX
    Explanations

    Conditional information or charged states

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

    classic riddles

    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
     replete
    0.43
     معظم
    0.42
     לך
    0.40
     समर्
    0.40
    顗
    0.40
     meantime
    0.39
     monolayer
    0.39
     welcomed
    0.38
     छे
    0.38
    咫
    0.38
    POSITIVE LOGITS
    এটা
    0.42
     Амери
    0.41
     Bedingungen
    0.41
    <0x9B>
    0.41
     eğer
    0.41
    amilton
    0.40
    
    0.40
     состояния
    0.40
    ziehungen
    0.40
    ，
    0.40
    Activations Density 0.001%

    No Known Activations