© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101729
    Prev
    Next
    INDEX
    Explanations

    following nouns or adjectives

    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
     a
    -1.59
     was
    -1.52
     même
    -1.48
     even
    -1.46
    -1.41
    même
    -1.40
     навіть
    -1.32
    白色的
    -1.32
     no
    -1.27
    ᷆
    -1.25
    POSITIVE LOGITS
    x
    1.22
     施設
    1.16
    ちん
    1.15
    Estos
    1.14
     correndo
    1.13
    齶
    1.13
    そうな
    1.13
    更好的
    1.12
     SUCH
    1.12
    Donations
    1.11
    Activations Density 0.182%

    No Known Activations