© 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. 10-GEMMASCOPE-RES-131K
    7. 75660
    Prev
    Next
    INDEX
    Explanations

    words starting with "vor"

    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
    which
    -3.27
    ]
    -2.53
    あるいは
    -2.47
    m
    -2.47
    ítimo
    -2.28
    Many
    -2.27
    Some
    -2.23
    Ⲉ
    -2.23
    :「
    -2.20
    二百
    -2.17
    POSITIVE LOGITS
    喾
    2.48
    ፨
    2.31
    礻
    2.25
    硨
    2.20
     已
    2.16
     allem
    2.14
     upsetting
    2.11
     Denken
    2.11
     insatiable
    2.08
    ные
    2.06
    Activations Density 0.001%

    No Known Activations