© 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. 98911
    Prev
    Next
    INDEX
    Explanations

    of X

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

    meaning, origin, metaphor

    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
     modifica
    0.50
     Umar
    0.49
     Qualcomm
    0.48
     Snapchat
    0.47
     compromises
    0.47
    WhatsApp
    0.46
     toning
    0.46
    鉞
    0.46
     WhatsApp
    0.46
     Olimpi
    0.46
    POSITIVE LOGITS
     સંબંધ
    0.47
    deut
    0.46
     மழை
    0.46
    kind
    0.44
    river
    0.44
    visitor
    0.44
     వర్
    0.44
    surf
    0.44
     reindeer
    0.43
    ön
    0.43
    Activations Density 0.001%

    No Known Activations