© 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. 62796
    Prev
    Next
    INDEX
    Explanations

    links and references

    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
     eager
    -0.99
     almost
    -0.97
     at
    -0.90
     some
    -0.90
     only
    -0.90
     just
    -0.89
     despite
    -0.85
    },[
    -0.85
     Following
    -0.85
     allow
    -0.85
    POSITIVE LOGITS
     OGSÅ
    1.01
     Dinas
    1.01
     ...]
    0.99
    brechen
    0.92
     também
    0.91
     ].
    0.91
     connecté
    0.91
     másik
    0.90
     /#
    0.90
     riguard
    0.89
    Activations Density 0.034%

    No Known Activations