© 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. 110122
    Prev
    Next
    INDEX
    Explanations

    whale names and types

    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
    London
    0.56
    PARTY
    0.55
    Cutting
    0.55
    Graham
    0.51
    British
    0.49
    Mush
    0.49
    맨
    0.49
    iphone
    0.48
    PRINC
    0.47
    敎
    0.46
    POSITIVE LOGITS
    sn
    0.66
     centroids
    0.64
    sı
    0.62
    sG
    0.62
     tasas
    0.60
     inclement
    0.58
     measured
    0.57
     malls
    0.57
     invertible
    0.55
     insurgency
    0.55
    Activations Density 0.000%

    No Known Activations