© 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. 73644
    Prev
    Next
    INDEX
    Explanations

    may express possibility

    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
    ometries
    -1.47
    brought
    -1.45
    vocations
    -1.41
    definitely
    -1.40
    личный
    -1.38
    ⸂
    -1.38
    )),
    -1.38
    easy
    -1.36
    ſſi
    -1.36
    乀
    -1.35
    POSITIVE LOGITS
     increase
    1.53
     because
    1.49
     now
    1.40
     start
    1.39
     antidote
    1.38
    zten
    1.38
     of
    1.36
    ",
    1.30
     increasingly
    1.27
     unteren
    1.27
    Activations Density 0.078%

    No Known Activations