© 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. 42415
    Prev
    Next
    INDEX
    Explanations

    asking or if

    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
     for
    -1.55
     a
    -1.27
     with
    -1.20
     based
    -1.14
     according
    -1.10
    各自
    -1.08
     tristesse
    -1.08
    machte
    -1.08
    ônus
    -1.04
     verifies
    -1.02
    POSITIVE LOGITS
     nasz
    1.41
     hierbei
    1.30
     pantallas
    1.30
    Appellee
    1.30
    ForeColor
    1.22
    Appellants
    1.20
     اینکه
    1.19
     zunächst
    1.18
     mientras
    1.16
     its
    1.13
    Activations Density 0.049%

    No Known Activations