© 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. 131949
    Prev
    Next
    INDEX
    Explanations

    time stamps or numbers

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

    discussing media or data

    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
    jir
    0.54
     кап
    0.52
    интере
    0.50
    ﺴ
    0.50
    evre
    0.49
    पिछले
    0.47
    economic
    0.47
    capi
    0.46
    лі
    0.46
    seguir
    0.46
    POSITIVE LOGITS
     arach
    0.49
     Neuro
    0.48
     HashTable
    0.47
     DBox
    0.47
    匏
    0.47
     ~(~)
    0.46
     Vantage
    0.46
     userId
    0.46
     lactose
    0.46
     Particle
    0.45
    Activations Density 0.002%

    No Known Activations