© 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. 3011
    Prev
    Next
    INDEX
    Explanations

    light sources

    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
     scoop
    0.48
    認め
    0.47
     shoots
    0.46
    班
    0.46
    らの
    0.45
     shoot
    0.45
     tsar
    0.44
     ね
    0.44
    യില
    0.44
     horde
    0.43
    POSITIVE LOGITS
    f
    0.66
    h
    0.64
    ik
    0.63
    ai
    0.61
    ang
    0.60
    have
    0.57
    ong
    0.55
    ex
    0.54
    ÉE
    0.54
    oc
    0.54
    Activations Density 0.001%

    No Known Activations