© 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. 54700
    Prev
    Next
    INDEX
    Explanations

    preposition followed by conceptual noun

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

    opportunities, careers, or destinations

    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
     ulterior
    0.56
     initiation
    0.52
    0.52
     married
    0.50
     (
    0.49
     Arbe
    0.48
     hierarchical
    0.48
     jawab
    0.47
     Z
    0.46
     tea
    0.46
    POSITIVE LOGITS
    𝙨
    0.48
    సీపీ
    0.47
     જેના
    0.46
     જેમાં
    0.46
    ♰
    0.46
    }}_
    0.46
    ksiyon
    0.46
    čin
    0.45
    药物
    0.44
    쳤
    0.43
    Activations Density 0.000%

    No Known Activations