© 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. 69294
    Prev
    Next
    INDEX
    Explanations

    newcomer or newbie

    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
    -
    -2.84
    }$
    -2.81
    <bos>
    -2.42
     '
    -2.39
     klassische
    -2.20
     heutige
    -2.19
     You
    -2.16
     innymi
    -2.09
    тесь
    -2.05
    』。
    -2.02
    POSITIVE LOGITS
    नलोड
    2.75
     They
    2.72
    ⢓
    2.61
    缡
    2.47
    尨
    2.30
    .’
    2.27
    comers
    2.23
     Says
    2.20
    hooter
    2.19
     unſ
    2.16
    Activations Density 0.002%

    No Known Activations