© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1978
    Prev
    Next
    INDEX
    Explanations

    feet, use

    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_16k_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
    padding
    0.40
    _
    0.40
     \%$
    0.38
     द्या
    0.38
    ্পনিক
    0.38
    form
    0.38
    timeout
    0.37
    _{
    0.37
    ッド
    0.37
    त्रियों
    0.36
    POSITIVE LOGITS
     nejen
    0.42
     wasn
    0.38
     سرکاری
    0.37
     especially
    0.36
     He
    0.36
    센
    0.35
    ICAN
    0.35
     empres
    0.34
    IAN
    0.34
     soprattutto
    0.34
    Activations Density 0.362%

    No Known Activations