© 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. 9737
    Prev
    Next
    INDEX
    Explanations

    describing emotional states

    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
    stellung
    0.31
    vian
    0.29
    зи
    0.29
    E
    0.28
     ఉన్నాయి
    0.27
    ner
    0.26
    pop
    0.26
     י
    0.26
    an
    0.26
    ria
    0.26
    POSITIVE LOGITS
     récupérer
    0.33
     médicament
    0.31
     bandana
    0.30
     kwenye
    0.30
     بهذا
    0.30
    ację
    0.29
     بشأن
    0.29
     déput
    0.29
     koj
    0.29
     นิด
    0.29
    Activations Density 0.052%

    No Known Activations