© 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. 99180
    Prev
    Next
    INDEX
    Explanations

    journalism and text messaging

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

    "Option" followed by text

    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
     свадь
    0.47
     गाडी
    0.44
     রাস্তা
    0.43
    婚礼
    0.43
     집
    0.42
     첫
    0.42
     프랑
    0.42
     پ
    0.42
     имуще
    0.41
     독일
    0.41
    POSITIVE LOGITS
     researching
    0.47
    <0x0D>
    0.41
     enough
    0.41
    ize
    0.41
    ・
    0.40
     Zealand
    0.40
    </h3>
    0.39
     Runner
    0.38
    _
    0.38
     discolor
    0.37
    Activations Density 0.002%

    No Known Activations