© 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. 35938
    Prev
    Next
    INDEX
    Explanations

    adverb + adjective/noun/verb

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

    requirements and conditions

    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
     addressing
    0.44
     سپورت
    0.43
     ensured
    0.43
     companion
    0.42
     NHS
    0.42
    𝗢
    0.42
    ன்ன
    0.40
    \}.
    0.40
     ensuring
    0.40
     manifested
    0.39
    POSITIVE LOGITS
    ाराम
    0.49
    egaard
    0.48
    rinth
    0.47
     धोने
    0.45
    älfte
    0.44
     தேர்த
    0.43
    चुरी
    0.43
     Contador
    0.43
    രം
    0.43
    íssimo
    0.43
    Activations Density 0.000%

    No Known Activations