© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60125
    Prev
    Next
    INDEX
    Explanations

    hidden locations and how to find them

    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
     ネックレス
    -1.15
     dekat
    -0.94
    ThemeOverlay
    -0.90
    ledad
    -0.89
     especially
    -0.88
    readFileSync
    -0.88
     станции
    -0.86
     also
    -0.84
     augusti
    -0.84
    hichever
    -0.84
    POSITIVE LOGITS
     tucked
    1.55
     inconspicuous
    1.54
     entrance
    1.38
     signage
    1.32
     hidden
    1.30
     unmarked
    1.19
    hidden
    1.17
     frontage
    1.13
     HID
    1.08
     exterior
    1.06
    Activations Density 0.030%

    No Known Activations