© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11515
    Prev
    Next
    INDEX
    Explanations

    social media following

    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
     zastos
    0.44
     ಔಷ
    0.42
     stains
    0.40
    吕
    0.40
    FLOAT
    0.39
     applicability
    0.39
     always
    0.38
    Dock
    0.38
    쇤
    0.38
     kebak
    0.38
    POSITIVE LOGITS
     Twitter
    0.95
     Instagram
    0.88
     twitter
    0.87
    Twitter
    0.84
     instagram
    0.82
     ट्विटर
    0.82
    Instagram
    0.80
     इंस्टाग्राम
    0.79
     follower
    0.75
    instagram
    0.75
    Activations Density 0.063%

    No Known Activations