© 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. 40-GEMMASCOPE-2-RES-65K
    7. 30
    Prev
    Next
    INDEX
    Explanations

    call or text 988

    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_40_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
    宻
    0.46
    fileName
    0.44
     riffs
    0.43
     erotic
    0.42
     gratuits
    0.40
    semblance
    0.39
     ذہن
    0.39
     masti
    0.39
    鲟
    0.39
     perceptible
    0.39
    POSITIVE LOGITS
     text
    0.99
     SMS
    0.89
     texted
    0.88
     texting
    0.81
    text
    0.80
     texts
    0.76
     Text
    0.75
    SMS
    0.75
     sms
    0.74
     TEXT
    0.73
    Activations Density 0.059%

    No Known Activations