© 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. 115578
    Prev
    Next
    INDEX
    Explanations

    vocational counselor

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

    explaining intent after verse

    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
     nodo
    0.46
     BIS
    0.45
     calcio
    0.45
     perfil
    0.44
    ):["
    0.43
     Sonic
    0.43
     nút
    0.42
    ोल
    0.42
     στά
    0.42
    脘
    0.42
    POSITIVE LOGITS
    nfasis
    0.55
     [])
    0.50
     おはよう
    0.48
    Telugu
    0.47
    bih
    0.47
    t
    0.46
    dire
    0.45
    chief
    0.45
    salas
    0.45
    bodied
    0.45
    Activations Density 0.000%

    No Known Activations