© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79668
    Prev
    Next
    INDEX
    Explanations

    A friend, Summer Heat, The Quit, In Situ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     their
    -1.38
     out
    -1.20
     that
    -1.15
     FOR
    -1.02
     for
    -1.02
     undeniably
    -0.99
     seemingly
    -0.98
    viale
    -0.96
     relentlessly
    -0.96
     Keep
    -0.94
    POSITIVE LOGITS
     mxArray
    1.02
    ætte
    1.01
    咐
    1.00
    ?』
    0.97
    がありますが
    0.97
    時間で
    0.96
    gebiete
    0.95
     "{\"
    0.94
    があり
    0.94
    などを
    0.94
    Activations Density 0.000%

    No Known Activations