© 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. 252125
    Prev
    Next
    INDEX
    Explanations

    specialist professions, fuels, fillers

    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
    都不是
    0.47
    Princip
    0.46
     препо
    0.46
    centric
    0.46
    Not
    0.44
    ĭ
    0.44
     This
    0.43
    ěř
    0.42
    November
    0.42
    涉及
    0.42
    POSITIVE LOGITS
     especialista
    0.51
     gasolina
    0.48
     psychologists
    0.48
     therapists
    0.48
     jadwal
    0.47
    ও
    0.45
     masukkan
    0.45
     chadd
    0.45
     butane
    0.45
     vets
    0.44
    Activations Density 0.002%

    No Known Activations