© 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. 23334
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

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

    sexually suggestive, exploit, abuse, endanger

    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
     yüzden
    0.60
     എന്റെ
    0.60
     प्रॉब्लम
    0.59
     거예요
    0.59
     meravigli
    0.59
     प्रॉब्ल
    0.58
     моего
    0.58
    唷
    0.57
     Deshalb
    0.57
     naprawdę
    0.57
    POSITIVE LOGITS
     with
    0.52
    WITH
    0.52
    ज
    0.52
    with
    0.51
    삶
    0.50
     needing
    0.49
    での
    0.48
    폄
    0.47
     स्थितियों
    0.46
     বিবেচনায়
    0.46
    Activations Density 0.077%

    No Known Activations