© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 53654
    Prev
    Next
    INDEX
    Explanations

    Harmonized System Code

    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
     त्या
    0.46
     softness
    0.45
     प्रतीत
    0.45
     appre
    0.44
     appreci
    0.43
    )-\
    0.43
     waveform
    0.43
     apprehension
    0.42
    さすが
    0.42
     insensible
    0.41
    POSITIVE LOGITS
    ουν
    0.53
    HEL
    0.51
    ÊN
    0.48
    CLAS
    0.48
    sset
    0.47
    েন্দ্রলাল
    0.47
     hudson
    0.46
    SEG
    0.46
     arbeiten
    0.46
    د
    0.46
    Activations Density 0.007%

    No Known Activations