© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 3092
    Prev
    Next
    INDEX
    Explanations

    introducing clarifications like i.e

    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
     feind
    -0.81
    版本的
    -0.78
    顺便
    -0.74
     Auß
    -0.74
    られました
    -0.72
    途中で
    -0.72
     rapp
    -0.71
     만화
    -0.71
    RESUM
    -0.71
    入り口
    -0.69
    POSITIVE LOGITS
     decir
    1.68
    OW
    1.57
     e
    1.52
     např
    1.52
     cioè
    1.43
     ie
    1.23
     example
    1.22
     например
    1.18
     Ie
    1.16
    例如
    1.09
    Activations Density 0.139%

    No Known Activations