© 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. 126331
    Prev
    Next
    INDEX
    Explanations

    sexual content, harmful, explicit

    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
    luž
    0.44
    superuser
    0.44
    ylene
    0.44
    ž
    0.44
     horrendous
    0.44
    лл
    0.43
    kHz
    0.42
    ែម
    0.42
    اءِ
    0.40
     sabbam
    0.39
    POSITIVE LOGITS
     conten
    0.49
    在意
    0.49
     qualifying
    0.48
    屐
    0.47
     contests
    0.45
     dislocations
    0.45
     workers
    0.44
     asymmetries
    0.44
     endorph
    0.44
     Οι
    0.43
    Activations Density 0.007%

    No Known Activations