© 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. 63814
    Prev
    Next
    INDEX
    Explanations

    has been, has enjoyed, asking questions

    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
     our
    -1.51
     we
    -1.48
     whilst
    -1.33
     nossas
    -1.23
    っております
    -1.20
     мені
    -1.20
     ourselves
    -1.20
     contemporánea
    -1.16
     meiner
    -1.16
     няколко
    -1.16
    POSITIVE LOGITS
    :
    1.62
     plenty
    1.48
     isn
    1.41
     his
    1.38
     —
    1.31
     wasn
    1.30
     “
    1.26
     another
    1.18
     hasn
    1.17
     advice
    1.16
    Activations Density 0.064%

    No Known Activations