© 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. 104316
    Prev
    Next
    INDEX
    Explanations

    party to date

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

    when followed by 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
    TRAS
    0.49
    IRONMENT
    0.49
    LOTRE
    0.48
     Require
    0.48
    厡
    0.48
     requiring
    0.47
    䢔
    0.47
    ITIES
    0.46
    軻
    0.46
     require
    0.46
    POSITIVE LOGITS
     salic
    0.44
     sulfon
    0.44
    گوید
    0.43
     бас
    0.42
     immun
    0.42
     subjectivity
    0.42
     वर्दी
    0.41
     субъек
    0.40
     cytotoxic
    0.40
    ひ
    0.40
    Activations Density 0.001%

    No Known Activations