© 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. 195155
    Prev
    Next
    INDEX
    Explanations

    interactive systems

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

    `if` clauses and `then` blocks

    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
    בי
    0.52
    fetchone
    0.50
    довж
    0.49
     wewnętr
    0.49
     memperbaiki
    0.49
    א
    0.48
    intégration
    0.47
     hoà
    0.47
    𝙖
    0.47
    ayutt
    0.47
    POSITIVE LOGITS
     Claire
    0.47
     Ended
    0.45
     Thinking
    0.45
     Конечно
    0.44
     to
    0.44
    yman
    0.44
    opters
    0.44
     Послед
    0.44
     মুক্তির
    0.43
     Evolutionary
    0.43
    Activations Density 0.003%

    No Known Activations