© 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. 49609
    Prev
    Next
    INDEX
    Explanations

    framing as harmless

    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
    Plas
    0.43
     Plas
    0.41
    க்கை
    0.39
     APPRO
    0.38
     ప్రా
    0.38
    銥
    0.38
    க்கோ
    0.37
    垠
    0.37
    Going
    0.37
     बाघ
    0.37
    POSITIVE LOGITS
     harmless
    0.74
     benign
    0.66
     legitimate
    0.64
     innocuous
    0.61
     stupidity
    0.53
     innoc
    0.53
     misunderstood
    0.52
     innocent
    0.51
     merely
    0.51
     legitt
    0.51
    Activations Density 0.151%

    No Known Activations