© 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. 102689
    Prev
    Next
    INDEX
    Explanations

    monuments

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

    weights and hyperparameters

    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
    Focus
    0.48
    Schwarz
    0.46
    FOCUS
    0.46
    Patients
    0.45
    亮度
    0.44
    စာ
    0.43
    Dogs
    0.43
    在
    0.43
    Ｐ
    0.43
    噻
    0.43
    POSITIVE LOGITS
     doubtful
    0.51
     diligence
    0.50
     diligent
    0.47
     religion
    0.46
     monument
    0.46
     weary
    0.46
     ruffle
    0.45
     luoghi
    0.45
     coolness
    0.45
     infirm
    0.44
    Activations Density 0.000%

    No Known Activations