© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46171
    Prev
    Next
    INDEX
    Explanations

    slurs and hate speech

    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
    ાદ
    0.41
    వంటి
    0.40
    മല്ല
    0.40
     ≠
    0.39
     Whose
    0.38
    ان
    0.38
     الداخلية
    0.38
    я
    0.38
     değil
    0.38
     Zo
    0.37
    POSITIVE LOGITS
     salivary
    0.45
     വായി
    0.45
    名古屋
    0.44
    ßerdem
    0.44
     cheveux
    0.44
    გენ
    0.43
    }\|^{
    0.43
     cityName
    0.41
    avons
    0.41
    🚅
    0.41
    Activations Density 0.001%

    No Known Activations