© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11584
    Prev
    Next
    INDEX
    Explanations

    recent news and updates

    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_40_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
     regole
    0.51
    ੋ
    0.47
     המת
    0.44
     rules
    0.43
     lifecycle
    0.42
     अगले
    0.42
    当初
    0.42
     incubation
    0.42
     périodes
    0.42
    ικές
    0.41
    POSITIVE LOGITS
     recente
    0.64
     недавно
    0.63
     (<
    0.61
     reciente
    0.60
     récente
    0.59
     Lately
    0.55
    (<
    0.54
    recently
    0.54
    সম্প্রতি
    0.54
     $(<
    0.54
    Activations Density 0.050%

    No Known Activations