© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 108695
    Prev
    Next
    INDEX
    Explanations

    income and success stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    жи
    0.52
    t
    0.52
    f
    0.52
    alkyl
    0.50
    zam
    0.46
    ient
    0.45
    l
    0.45
    v
    0.45
    bin
    0.43
    iever
    0.41
    POSITIVE LOGITS
     photographing
    0.59
     archiving
    0.52
     estimating
    0.52
     যোদ্ধা
    0.51
     photographs
    0.50
     csp
    0.50
     storing
    0.50
     dumbbells
    0.50
     envisions
    0.50
     allowNull
    0.50
    Activations Density 0.001%

    No Known Activations