© 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-65K
    7. 54201
    Prev
    Next
    INDEX
    Explanations

    rather than explicit or intended

    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
     confes
    0.42
    ეხ
    0.39
    Rhe
    0.39
     রচিত
    0.39
    Suppress
    0.39
    燐
    0.39
    Needless
    0.38
    美麗
    0.38
     dakkh
    0.38
     microcos
    0.38
    POSITIVE LOGITS
     nefarious
    0.59
     intending
    0.56
     قصد
    0.50
     intention
    0.50
     intends
    0.49
     intend
    0.48
     malicious
    0.47
     intended
    0.46
    intend
    0.46
     악
    0.45
    Activations Density 0.221%

    No Known Activations