© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32520
    Prev
    Next
    INDEX
    Explanations

    I followed by assumptions or thoughts

    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
    Dimensi
    -0.85
    Continua
    -0.84
    zepte
    -0.84
    ථ
    -0.83
    Paket
    -0.81
    อาจ
    -0.81
     pietra
    -0.80
     profesor
    -0.80
     ضروری
    -0.80
    Laughs
    -0.79
    POSITIVE LOGITS
     assume
    4.81
     assumption
    4.00
    assume
    3.91
     assumes
    3.88
     Assume
    3.73
    Assume
    3.69
     assuming
    3.69
     presume
    3.55
     assumed
    3.53
     assumptions
    3.31
    Activations Density 0.120%

    No Known Activations