© 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. 31-GEMMASCOPE-2-RES-262K
    7. 33227
    Prev
    Next
    INDEX
    Explanations

    abuse, illness, damaging

    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_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
    s
    0.46
    Target
    0.45
    template
    0.41
    Iterator
    0.40
    File
    0.40
    t
    0.39
    Camera
    0.39
    ());
    0.39
    kernel
    0.39
    ም
    0.38
    POSITIVE LOGITS
     vacanam
    0.45
     litres
    0.45
     Turned
    0.43
     sabah
    0.42
     perang
    0.42
     poprzed
    0.42
     innermost
    0.41
     pró
    0.40
     linkCell
    0.40
     utilis
    0.40
    Activations Density 0.000%

    No Known Activations