© 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. 151206
    Prev
    Next
    INDEX
    Explanations

    heartbeat accelerate, Successfully Subscribed

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

    decoding and processing text

    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
    黃
    0.46
     darker
    0.44
     chłop
    0.44
     bảo
    0.44
    姜
    0.44
    黄
    0.43
     vàng
    0.43
     guérison
    0.43
     पुनर्
    0.43
     захи
    0.43
    POSITIVE LOGITS
    v
    0.45
    aghan
    0.43
     وسي
    0.42
     اد
    0.42
    adia
    0.41
    ahal
    0.41
     operativos
    0.40
     ©
    0.40
     encargado
    0.39
    ende
    0.38
    Activations Density 0.003%

    No Known Activations