© 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. 83217
    Prev
    Next
    INDEX
    Explanations

    state vector

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

    state function

    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
     thí
    0.41
     تقريبا
    0.38
    طرف
    0.37
    实验
    0.37
     testers
    0.37
    чнее
    0.37
     sulfite
    0.37
    瘾
    0.37
    罨
    0.36
     trigonometric
    0.36
    POSITIVE LOGITS
    params
    0.50
    STATE
    0.46
     futuras
    0.46
    state
    0.44
    =\{
    0.43
     STATE
    0.42
    集合
    0.42
     describing
    0.42
    State
    0.41
     actualizada
    0.41
    Activations Density 0.034%

    No Known Activations