© 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. 186242
    Prev
    Next
    INDEX
    Explanations

    instructions, strain, linking, joined, release, exchange

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

    parameters and assignments

    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
    Todo
    0.50
    地理
    0.49
    表达式
    0.48
    აგ
    0.48
    Ге
    0.47
    Т
    0.47
    Shares
    0.46
    Ж
    0.45
    𝙜
    0.45
    UK
    0.45
    POSITIVE LOGITS
     René
    0.54
     SAE
    0.51
    intervento
    0.51
    acés
    0.50
     Schumann
    0.50
    pant
    0.49
     Jameson
    0.49
    eyer
    0.48
     Ravenna
    0.48
     Pantheon
    0.47
    Activations Density 0.001%

    No Known Activations