© 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. 24814
    Prev
    Next
    INDEX
    Explanations

    defamation and malicious actions

    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
    <0xCF>
    0.45
     индика
    0.44
    rique
    0.43
    segn
    0.41
     inesper
    0.41
    betrieb
    0.40
     Конечно
    0.40
    电阻
    0.40
     편리
    0.40
    неоп
    0.40
    POSITIVE LOGITS
     defamation
    1.16
     defamatory
    1.09
     slander
    1.02
     libel
    0.97
    诽
    0.91
     defam
    0.89
     publication
    0.78
     publications
    0.73
    誹
    0.70
    诬
    0.68
    Activations Density 0.037%

    No Known Activations