© 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. 12579
    Prev
    Next
    INDEX
    Explanations

    negative service complaints

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

    unacceptable, anger, complaints

    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
     spannend
    0.47
     :)
    0.46
    😉
    0.46
    ☺
    0.46
     Compose
    0.45
    ografie
    0.45
     Descriptive
    0.45
     ஆரோ
    0.45
     =)
    0.45
     ;)
    0.44
    POSITIVE LOGITS
    🤬
    0.95
    😡
    0.89
     disgusting
    0.89
     NEVER
    0.78
     horrible
    0.75
     incompetent
    0.74
     disgraceful
    0.73
     incompetence
    0.73
     appalling
    0.72
     horrendous
    0.71
    Activations Density 0.071%

    No Known Activations