© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 31192
    Prev
    Next
    INDEX
    Explanations

    Let's look at why

    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_65k_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
    মুনা
    0.45
     axisymmetric
    0.44
    ဆက်
    0.43
    Bokeh
    0.43
     bokeh
    0.43
     투
    0.42
    ⇅
    0.42
    widet
    0.42
    :'],
    0.42
    🛸
    0.42
    POSITIVE LOGITS
     knowledge
    0.46
     candidates
    0.45
     Knowledge
    0.44
     Зна
    0.42
    Knowledge
    0.41
     неправи
    0.41
     candidate
    0.41
    candidate
    0.40
     канди
    0.40
     знания
    0.39
    Activations Density 0.155%

    No Known Activations