© 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. 63817
    Prev
    Next
    INDEX
    Explanations

    specific names followed by titles

    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
     cruiser
    -0.90
    Princess
    -0.81
     príncipe
    -0.79
    Prince
    -0.78
    Discovery
    -0.77
    cruiser
    -0.77
     Trekking
    -0.76
     BLU
    -0.75
     Barbar
    -0.74
    Bella
    -0.73
    POSITIVE LOGITS
     يف
    0.81
     thinking
    0.75
     thoughts
    0.71
    gpg
    0.70
     fortemente
    0.68
     costo
    0.66
     lodging
    0.66
     tubes
    0.66
    χα
    0.65
     экра
    0.65
    Activations Density 0.051%

    No Known Activations