© 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. 59569
    Prev
    Next
    INDEX
    Explanations

    hypothetical or conditional statements

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

    if clauses

    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
    គាត់
    0.43
     probablement
    0.43
     সমাধ
    0.41
     veldig
    0.41
     taker
    0.40
     Surg
    0.40
     細
    0.40
     സമയ
    0.39
    inaire
    0.38
     सेंचुरी
    0.38
    POSITIVE LOGITS
     somewhat
    0.41
     clichés
    0.41
    声音
    0.40
     என்றால்
    0.40
     entonces
    0.40
     dunque
    0.40
     dúvidas
    0.39
    までは
    0.39
    ἆ
    0.39
    垢
    0.38
    Activations Density 0.059%

    No Known Activations