© 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. 35923
    Prev
    Next
    INDEX
    Explanations

    leave it, feeling of

    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
    航
    0.48
    沦
    0.44
    ాత
    0.44
     প্রতিনি
    0.44
     актив
    0.43
     constantemente
    0.43
    ௫
    0.43
    աշ
    0.42
     പ്രവർ
    0.42
    лық
    0.42
    POSITIVE LOGITS
    parents
    0.46
     Sunday
    0.44
     είχε
    0.44
     got
    0.43
     Korea
    0.42
     हेयर
    0.42
     Phon
    0.41
     gahet
    0.41
     Kids
    0.40
     Reichs
    0.40
    Activations Density 0.014%

    No Known Activations