© 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-65K
    7. 40982
    Prev
    Next
    INDEX
    Explanations

    causing negative outcomes

    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_65k_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
     کوي
    0.70
    یی
    0.68
    ي
    0.65
    rógeno
    0.63
    ചര്യ
    0.63
     možnost
    0.62
    ți
    0.61
     combustível
    0.61
     নিয়ন্ত্র
    0.60
     возможностей
    0.60
    POSITIVE LOGITS
    v
    0.81
    _
    0.76
    2
    0.75
    d
    0.66
    m
    0.66
    g
    0.66
    b
    0.60
    st
    0.59
    .
    0.59
     havoc
    0.59
    Activations Density 0.047%

    No Known Activations