© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77228
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    änderung
    -0.88
     OMITBAD
    -0.85
    țial
    -0.83
     )}$
    -0.82
    бражение
    -0.82
    pography
    -0.81
    innerHeight
    -0.80
     fikk
    -0.80
    }}
    -0.80
    gné
    -0.77
    POSITIVE LOGITS
     filled
    0.77
    Should
    0.76
    离去
    0.75
    He
    0.74
     dữ
    0.73
     erw
    0.70
     positioned
    0.69
    胜
    0.69
     indisputable
    0.69
     optimistic
    0.68
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.