© 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. 57213
    Prev
    Next
    INDEX
    Explanations

    listing items among others

    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
     or
    -2.22
     two
    -1.51
     three
    -1.44
     twice
    -1.21
     four
    -1.21
     five
    -1.20
     sufficient
    -1.17
     nine
    -1.16
     more
    -1.16
     sometimes
    -1.13
    POSITIVE LOGITS
     including
    2.25
    INCLUDING
    1.80
    besides
    1.80
     közül
    1.77
    including
    1.74
     INCLUDING
    1.74
    Including
    1.71
     besides
    1.70
     incluindo
    1.63
     både
    1.57
    Activations Density 0.177%

    No Known Activations