© 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-262K
    7. 83955
    Prev
    Next
    INDEX
    Explanations

    He first following ambled shuffled

    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_262k_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
     Mail
    0.53
     Z
    0.52
     k
    0.51
     Augusta
    0.46
     All
    0.45
     Air
    0.45
     FAQs
    0.45
     Merger
    0.45
     Influence
    0.44
     Entrepreneur
    0.44
    POSITIVE LOGITS
    ת
    0.53
    нти
    0.50
    Kaynak
    0.50
     richiest
    0.50
    церт
    0.49
    etermined
    0.48
    áte
    0.46
    NOWLED
    0.45
     fixé
    0.43
     വിവിധ
    0.43
    Activations Density 0.006%

    No Known Activations