© 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. 105696
    Prev
    Next
    INDEX
    Explanations

    author initials in citations

    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
     about
    -2.16
     all
    -1.59
     our
    -1.43
     reconocido
    -1.38
    :
    -1.36
     a
    -1.34
    ]
    -1.33
     between
    -1.30
     ответствен
    -1.30
     нашем
    -1.24
    POSITIVE LOGITS
    *',
    1.38
     شما
    1.35
     hvis
    1.33
    magem
    1.30
     ausdrück
    1.29
    ERALD
    1.28
    גרפיה
    1.27
    ఞ
    1.27
    Bibliografie
    1.23
     Theſe
    1.23
    Activations Density 0.017%

    No Known Activations