© 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. 63115
    Prev
    Next
    INDEX
    Explanations

    what's the point

    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
     возможность
    -1.34
     mêmes
    -1.33
     GETTING
    -1.27
    genden
    -1.20
     Boletín
    -1.15
     Möglichkeit
    -1.14
     mesmos
    -1.13
     Mentioned
    -1.13
     germain
    -1.13
     obvio
    -1.12
    POSITIVE LOGITS
     difference
    1.63
     next
    1.63
     really
    1.53
     exact
    1.52
     best
    1.46
     most
    1.45
     specific
    1.43
     biggest
    1.43
     actual
    1.42
     status
    1.37
    Activations Density 0.065%

    No Known Activations