© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8174
    Prev
    Next
    INDEX
    Explanations

    and spending go me jail

    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
    arc
    0.47
    time
    0.46
     drip
    0.46
     Unit
    0.45
    decay
    0.45
    '
    0.45
    અમ
    0.45
     caring
    0.44
    L
    0.44
     Decay
    0.44
    POSITIVE LOGITS
     الك
    0.48
     seçenek
    0.48
     وال
    0.47
     أو
    0.47
     الا
    0.46
     لأنه
    0.46
     также
    0.45
     بس
    0.45
     مبار
    0.45
     కూడా
    0.45
    Activations Density 0.048%

    No Known Activations