© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 28422
    Prev
    Next
    INDEX
    Explanations

    story starter prompts

    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
     can
    1.05
     has
    0.99
    a
    0.96
     are
    0.92
     is
    0.91
     of
    0.87
    5
    0.87
    are
    0.84
     to
    0.84
    im
    0.82
    POSITIVE LOGITS
    nieuw
    0.77
     هنتكلم
    0.74
     जिसमे
    0.74
    行う
    0.69
    jelen
    0.69
     তুলনায়
    0.66
    س
    0.66
    bbero
    0.65
     લઇ
    0.65
    젼
    0.65
    Activations Density 0.522%

    No Known Activations