© 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. 110278
    Prev
    Next
    INDEX
    Explanations

    investigation and communication

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

    dream journal research paper

    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
    魃
    0.48
     Jahrhund
    0.48
     Pemer
    0.47
    ához
    0.47
     Statute
    0.46
    క్కి
    0.46
     Kamm
    0.46
    üge
    0.44
     تھے۔
    0.44
    బాద్
    0.44
    POSITIVE LOGITS
    ated
    0.50
     dressed
    0.47
     đ
    0.46
     গ
    0.46
     самых
    0.46
    ust
    0.46
     awkwardly
    0.45
    bat
    0.45
    ictions
    0.44
     toughest
    0.44
    Activations Density 0.000%

    No Known Activations