© 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. 149002
    Prev
    Next
    INDEX
    Explanations

    on followed by dates

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

    more expensive

    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
    XO
    0.46
    isection
    0.44
    堂
    0.42
    arnell
    0.42
    Cache
    0.41
    aget
    0.41
    hen
    0.41
     armature
    0.41
    PLL
    0.41
    驰
    0.41
    POSITIVE LOGITS
     clôt
    0.53
     cierre
    0.50
     durable
    0.46
    പ്പ്
    0.46
     accompagnée
    0.46
     बँके
    0.46
     fermeture
    0.45
     année
    0.45
    রাষ্ট্র
    0.44
     Bankers
    0.44
    Activations Density 0.001%

    No Known Activations