© 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. 19756
    Prev
    Next
    INDEX
    Explanations

    when we use or need

    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
    grafik
    -1.35
    ]\\
    -1.27
     aantal
    -1.25
    ateľ
    -1.22
    tagonal
    -1.21
    sver
    -1.19
    kelijkheid
    -1.18
    yyb
    -1.17
     Öl
    -1.17
     felb
    -1.16
    POSITIVE LOGITS
     reason
    1.24
    f
    1.23
    “
    1.22
     bestimmte
    1.14
     where
    1.13
     place
    1.11
    </em>
    1.11
    It
    1.09
     things
    1.09
     these
    1.08
    Activations Density 0.076%

    No Known Activations