© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9067
    Prev
    Next
    INDEX
    Explanations

    hat and hate

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

    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-pt/resid_post/layer_40_width_16k_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
     председа
    0.46
    
    0.45
    ⬤
    0.43
    )\|_{
    0.43
    戤
    0.43
    HEADER
    0.42
    
    0.42
    煅
    0.42
    ická
    0.41
     pedibusque
    0.41
    POSITIVE LOGITS
     Hat
    0.61
    Hat
    0.61
    hat
    0.59
     hat
    0.58
     hats
    0.51
     Hats
    0.45
    chat
    0.45
     hatt
    0.44
    ¯
    0.44
    ˆ
    0.42
    Activations Density 0.085%

    No Known Activations