© 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. 219360
    Prev
    Next
    INDEX
    Explanations

    used clothing, temp changes, first economically, buy locally, rather than

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

    scripts breaking, volatility, limiting flexibility

    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
     गुण
    0.50
     という
    0.44
     ৫৮
    0.44
    ळ
    0.42
    никами
    0.42
    ちょ
    0.42
     น่ะ
    0.42
    addition
    0.41
     सुविधाओं
    0.41
    ں
    0.41
    POSITIVE LOGITS
    ଷ୍
    0.46
    te
    0.45
     tremors
    0.45
     javac
    0.44
    criptive
    0.44
     стрелецкой
    0.44
     terá
    0.43
     patties
    0.43
     underwent
    0.42
    ienced
    0.42
    Activations Density 0.000%

    No Known Activations