© 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. 50889
    Prev
    Next
    INDEX
    Explanations

    conditional statements about fear or choices

    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
     damals
    0.44
    ﹁
    0.42
    Uc
    0.41
    ˟
    0.41
    ロッパ
    0.41
    ύτε
    0.39
    Objs
    0.39
    =[-
    0.39
     вскоре
    0.39
    űt
    0.39
    POSITIVE LOGITS
     analytics
    0.40
     Arctic
    0.39
     your
    0.39
    ضيف
    0.38
    ్యాచ్
    0.38
     waivers
    0.38
     Express
    0.38
    는
    0.38
     Sustain
    0.38
     شما
    0.38
    Activations Density 0.021%

    No Known Activations