© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80959
    Prev
    Next
    INDEX
    Explanations

    think you

    np_acts-logits-general · gemini-2.5-flash-lite

    instructions and negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    0.50
    バリー
    0.45
     sweater
    0.44
    yler
    0.44
    ứt
    0.43
     vel
    0.42
    ientemente
    0.42
    /
    0.41
    с
    0.41
    air
    0.40
    POSITIVE LOGITS
     Describes
    0.49
     Escuela
    0.49
    Ἁ
    0.49
    餑
    0.47
    मील
    0.47
     Palo
    0.46
     Scuola
    0.46
    Crow
    0.46
     École
    0.46
    রোগ
    0.45
    Activations Density 0.001%

    No Known Activations