© 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. 33122
    Prev
    Next
    INDEX
    Explanations

    explicit sexual content and body descriptions

    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
    ad
    0.54
    ed
    0.51
    en
    0.50
    ehl
    0.50
    י
    0.50
    in
    0.49
    e
    0.48
    ת
    0.47
    ep
    0.47
    eh
    0.47
    POSITIVE LOGITS
     calcular
    0.49
     miniatures
    0.46
     larynx
    0.45
     primeros
    0.44
     SERVICES
    0.42
     ordres
    0.42
     glucose
    0.42
     PLASMA
    0.42
     outline
    0.41
    计算
    0.41
    Activations Density 0.001%

    No Known Activations