© 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. 22-GEMMASCOPE-RES-131K
    7. 129275
    Prev
    Next
    INDEX
    Explanations

    different variations

    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_22/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
     або
    -1.07
    LOGICAL
    -0.99
    帖最后由
    -0.98
     parseFloat
    -0.96
     or
    -0.94
     racconta
    -0.94
     infuriating
    -0.93
    étude
    -0.93
    ABOVE
    -0.93
     coronav
    -0.93
    POSITIVE LOGITS
     разных
    1.30
     różnych
    1.28
     things
    1.27
     today
    1.26
     diferentes
    1.20
     people
    1.16
     différentes
    1.15
     détruit
    1.12
     diversas
    1.09
     different
    1.08
    Activations Density 0.020%

    No Known Activations