© 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. 1673
    Prev
    Next
    INDEX
    Explanations

    have a

    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
    aceae
    0.49
     being
    0.48
    나
    0.48
     deixando
    0.47
    čku
    0.47
     mankind
    0.46
     Being
    0.46
     mythological
    0.44
    다면
    0.44
     inhabited
    0.43
    POSITIVE LOGITS
     recours
    0.72
    ע
    0.66
     confidence
    0.63
    ল
    0.63
     acesso
    0.62
     acceso
    0.61
     doubts
    0.61
     conversations
    0.59
     recourse
    0.59
    ן
    0.59
    Activations Density 0.236%

    No Known Activations