© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151666
    Prev
    Next
    INDEX
    Explanations

    bring about

    np_acts-logits-general · gemini-2.5-flash-lite

    refuse requests for inappropriate content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ك
    0.46
     Reigns
    0.45
    大
    0.44
    లపై
    0.41
     $$\
    0.41
     Dentistry
    0.41
     the
    0.40
    housing
    0.39
    提前
    0.39
    [\
    0.38
    POSITIVE LOGITS
     elektron
    0.51
    გნ
    0.48
     informasjon
    0.48
     amikor
    0.48
    спублі
    0.48
     weatherproof
    0.47
     परस्पर
    0.46
     intravascular
    0.46
     pej
    0.46
    ᙱ
    0.46
    Activations Density 0.001%

    No Known Activations