© 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. 1608
    Prev
    Next
    INDEX
    Explanations

    experience

    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
     प्रार्थना
    0.48
     negate
    0.45
    बु
    0.44
    బు
    0.44
    juč
    0.44
    ете
    0.42
     excel
    0.41
    壮
    0.41
     છીએ
    0.41
     existential
    0.40
    POSITIVE LOGITS
     DMA
    0.50
     Whitehall
    0.50
    rn
    0.47
    renner
    0.46
    rawberry
    0.45
    dmg
    0.44
     réaction
    0.44
    hf
    0.44
    mountable
    0.44
    rg
    0.43
    Activations Density 0.000%

    No Known Activations