© 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. 31792
    Prev
    Next
    INDEX
    Explanations

    help variations

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

    "Character Map" or "Hope this helps!"

    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
    arid
    0.46
    acek
    0.44
    itling
    0.44
    挑战
    0.43
    হ
    0.43
     Racing
    0.42
     samtidigt
    0.42
    ๆ
    0.42
     âge
    0.41
    года
    0.41
    POSITIVE LOGITS
     composta
    0.45
    ጢ
    0.45
    텨
    0.44
     informally
    0.43
     ransom
    0.42
     পৃষ্ঠা
    0.42
     rmse
    0.42
     convo
    0.42
    rogram
    0.42
     Prepare
    0.41
    Activations Density 0.000%

    No Known Activations