© 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. 99697
    Prev
    Next
    INDEX
    Explanations

    clause starters

    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
    ndash
    -0.99
    cedent
    -0.98
     mía
    -0.96
    €”
    -0.89
    sistant
    -0.86
     dětí
    -0.86
    aces
    -0.85
    complish
    -0.82
    eten
    -0.82
    pte
    -0.82
    POSITIVE LOGITS
     seem
    1.01
     is
    0.99
     got
    0.97
     cannot
    0.96
     came
    0.90
     which
    0.85
     seems
    0.84
     remotely
    0.82
     downed
    0.82
     metamor
    0.80
    Activations Density 0.015%

    No Known Activations