© 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. 163342
    Prev
    Next
    INDEX
    Explanations

    estimates from

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

    date, Image, or, deep

    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
    Matter
    0.49
     Matters
    0.46
    றுத்த
    0.45
    迷
    0.44
     колеба
    0.44
    Programm
    0.43
    侦
    0.43
    䒺
    0.43
     أهم
    0.42
     neun
    0.42
    POSITIVE LOGITS
    า
    0.45
    have
    0.44
     представи
    0.43
     kêu
    0.43
    ACING
    0.43
     recognise
    0.42
     tradicion
    0.42
     ancor
    0.42
     resta
    0.42
     recognition
    0.42
    Activations Density 0.001%

    No Known Activations