© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31204
    Prev
    Next
    INDEX
    Explanations

    taking for granted or leadership

    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_34/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
     Contr
    -0.91
    izde
    -0.88
    kaŭ
    -0.81
     Industria
    -0.79
    cheme
    -0.79
    🤏
    -0.78
     Welt
    -0.78
    дино
    -0.78
     unreachable
    -0.76
     MEMOR
    -0.75
    POSITIVE LOGITS
     taken
    3.48
    taken
    2.69
     take
    2.66
    Taken
    2.50
     Taken
    2.22
    Take
    2.22
     Take
    2.22
    take
    1.98
     TAKEN
    1.95
     took
    1.83
    Activations Density 0.025%

    No Known Activations