© 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. 78237
    Prev
    Next
    INDEX
    Explanations

    round of

    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
     débuts
    -0.94
    पु
    -0.91
    のよう
    -0.89
     situation
    -0.86
    何度も
    -0.86
    ᥆
    -0.86
     cómoda
    -0.85
    Lys
    -0.84
     понравилось
    -0.83
     continuamente
    -0.82
    POSITIVE LOGITS
     of
    1.43
     interviews
    1.19
     infections
    1.08
     attacks
    1.05
     emails
    1.03
    ของ
    1.02
     killings
    0.97
     applause
    0.96
     appointments
    0.94
     layoffs
    0.93
    Activations Density 0.036%

    No Known Activations