© 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. 12090
    Prev
    Next
    INDEX
    Explanations

    tokens after specific words

    np_acts-logits-general · gemini-2.5-flash-lite

    HTML or code formatting elements, particularly markup tags and special characters like ampersands and non-breaking spaces.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     our
    -1.57
    }
    -1.50
     or
    -1.45
    )
    -1.45
     srdce
    -1.41
    mohon
    -1.38
     rápidamente
    -1.38
    ଝ
    -1.38
     celebrado
    -1.34
    ,
    -1.34
    POSITIVE LOGITS
     They
    1.75
    since
    1.73
    although
    1.59
    峮
    1.55
    这也是
    1.54
     всех
    1.51
     seperti
    1.50
     they
    1.50
     Они
    1.50
     塗装
    1.49
    Activations Density 0.000%

    No Known Activations