© 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. 162885
    Prev
    Next
    INDEX
    Explanations

    legal route

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

    words following "and"

    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
    どう
    0.56
    م
    0.52
    горь
    0.50
    々は
    0.50
    к
    0.50
     Archbishop
    0.49
     молеку
    0.48
    ВА
    0.48
    МА
    0.48
     номера
    0.48
    POSITIVE LOGITS
    lova
    0.58
    Shader
    0.51
    :
    0.51
    Ic
    0.51
    loge
    0.50
    一面
    0.48
    puter
    0.48
    Alo
    0.48
    val
    0.48
    plings
    0.48
    Activations Density 0.000%

    No Known Activations