© 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-16K
    7. 8386
    Prev
    Next
    INDEX
    Explanations

    expressions of desire and request

    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_16k_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
    ध
    0.36
    気を
    0.35
    الح
    0.34
    لد
    0.34
    ہم
    0.34
    協会
    0.33
    Civita
    0.32
    햐
    0.32
    явление
    0.32
    غ
    0.32
    POSITIVE LOGITS
     surm
    0.40
     requested
    0.38
    čni
    0.38
    in
    0.38
     taxonom
    0.37
    äts
    0.37
     remarked
    0.36
     statt
    0.35
     в
    0.34
    rétaire
    0.34
    Activations Density 0.088%

    No Known Activations