© 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. 90373
    Prev
    Next
    INDEX
    Explanations

    progressively reaching a threshold

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

    gradual progression or consequence

    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
     containing
    0.42
    the
    0.39
     preparatory
    0.39
     soldering
    0.38
     preparing
    0.37
    these
    0.37
    ဲ
    0.37
     components
    0.37
     confidently
    0.37
    ндарт
    0.37
    POSITIVE LOGITS
     progressivement
    0.51
    🥵
    0.46
    🥲
    0.43
     지속
    0.43
    渐渐
    0.43
    ukiy
    0.43
    🥹
    0.42
     फूल
    0.42
     evolves
    0.42
     koş
    0.42
    Activations Density 0.002%

    No Known Activations