© 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. 61887
    Prev
    Next
    INDEX
    Explanations

    documentary below

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

    information, history, and discovered value

    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
     secures
    0.57
    ками
    0.51
     hesitated
    0.51
     generates
    0.50
     বৃদ্ধি
    0.49
     liberated
    0.49
     disrupts
    0.48
    恝
    0.48
    fecha
    0.47
     আয়ন
    0.47
    POSITIVE LOGITS
     inspectors
    0.52
     Impulse
    0.50
     innen
    0.49
    Luther
    0.48
    係
    0.48
     Inspectors
    0.48
    互联网档案馆
    0.47
    里克
    0.47
    业内
    0.47
    Vol
    0.47
    Activations Density 0.000%

    No Known Activations