© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13765
    Prev
    Next
    INDEX
    Explanations

    truth value of statements

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

    statement, premise, opinion

    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_16k_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
    olz
    0.45
    虍
    0.45
    𝙥
    0.44
    埬
    0.43
    τροπ
    0.43
    ្សែ
    0.43
    还将
    0.42
     *\
    0.42
    SY
    0.42
    ittance
    0.42
    POSITIVE LOGITS
     statement
    1.09
     statements
    1.06
     Statements
    1.06
    statement
    1.04
     Statement
    0.97
     कथन
    0.96
    Statements
    0.96
    statements
    0.95
    Statement
    0.93
     pernyataan
    0.87
    Activations Density 0.107%

    No Known Activations