© 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. 14748
    Prev
    Next
    INDEX
    Explanations

    quotation marks followed by text

    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
     new
    -1.25
     this
    -1.20
    岂
    -1.20
     not
    -1.20
     không
    -1.17
    aa
    -1.16
    資金
    -1.16
     current
    -1.16
     valuable
    -1.13
     other
    -1.11
    POSITIVE LOGITS
    盉
    1.38
    selben
    1.33
     gewor
    1.31
    responsible
    1.27
    himself
    1.27
    Privatpatient
    1.25
    selbe
    1.22
     Игра
    1.21
    meant
    1.20
     STRONG
    1.20
    Activations Density 0.002%

    No Known Activations