© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12335
    Prev
    Next
    INDEX
    Explanations

    hills and mountains

    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_10/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
    шні
    -1.33
     RECOMEND
    -1.30
     even
    -1.19
     PARKING
    -1.16
     AVAILABILITY
    -1.14
     когато
    -1.13
     NEGRO
    -1.13
    امت
    -1.12
     AGUA
    -1.11
    when
    -1.08
    POSITIVE LOGITS
     ältere
    1.26
    šech
    1.13
     голос
    1.08
     hills
    1.05
     hill
    1.02
     печени
    1.01
     mountain
    0.98
     höchste
    0.94
     größere
    0.93
    estroying
    0.93
    Activations Density 0.057%

    No Known Activations