© 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. 16-GEMMASCOPE-2-RES-262K
    7. 28569
    Prev
    Next
    INDEX
    Explanations

    trigonometric identities and ratios

    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_16_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
    urgent
    0.61
    IAT
    0.59
    如果您
    0.58
     ascendent
    0.58
    yay
    0.57
    喲
    0.57
    requires
    0.55
    由於
    0.55
    i
    0.55
     कांच
    0.55
    POSITIVE LOGITS
     l
    0.66
     be
    0.65
     pantai
    0.65
     vals
    0.61
     to
    0.59
     harga
    0.59
     lx
    0.58
     kota
    0.56
     identidade
    0.55
     shingles
    0.55
    Activations Density 0.014%

    No Known Activations