© 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. 1759
    Prev
    Next
    INDEX
    Explanations

    approaches to topics

    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
    olate
    0.48
    ለጠ
    0.45
    herlands
    0.44
    际
    0.44
    บ
    0.43
    categor
    0.42
    iteits
    0.42
    ழ
    0.42
    扡
    0.42
    Segment
    0.41
    POSITIVE LOGITS
     antiguos
    0.47
     gemeinsam
    0.46
     együtt
    0.45
    ,*
    0.44
     вместе
    0.43
     turbocharged
    0.43
     ventured
    0.42
     سي
    0.42
     anciens
    0.42
     labored
    0.41
    Activations Density 0.063%

    No Known Activations