© 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. 107000
    Prev
    Next
    INDEX
    Explanations

    third coordinate

    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
    Secondly
    -0.89
     Secondly
    -0.87
     الثاني
    -0.82
    wnętr
    -0.78
     really
    -0.77
    FMT
    -0.76
     secondly
    -0.76
    formKey
    -0.76
    пью
    -0.76
     second
    -0.75
    POSITIVE LOGITS
     third
    1.43
     depth
    1.36
    Third
    1.29
     Third
    1.17
    depth
    1.16
    third
    1.15
     z
    1.14
     треть
    1.13
     Thirdly
    1.11
    THIRD
    1.08
    Activations Density 0.027%

    No Known Activations