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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7200
    Prev
    Next
    INDEX
    Explanations

    addresses and locations

    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
     g
    0.53
    ierung
    0.50
     Custom
    0.49
     k
    0.48
     Generic
    0.47
     m
    0.44
     h
    0.44
     C
    0.43
     c
    0.43
    :
    0.43
    POSITIVE LOGITS
     miasta
    0.51
     городе
    0.46
    ската
    0.44
    ཊ
    0.44
    हाबाद
    0.44
     столи
    0.43
     urbana
    0.43
     শহরে
    0.43
    》。
    0.42
     città
    0.42
    Activations Density 0.007%

    No Known Activations