© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 17021
    Prev
    Next
    INDEX
    Explanations

    historical and emerging important details

    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
     Aí
    0.53
     blessings
    0.51
     ambiguities
    0.50
     clás
    0.47
     élég
    0.47
     cláss
    0.46
     事
    0.46
     algebras
    0.45
     Име
    0.45
     მს
    0.45
    POSITIVE LOGITS
     yılında
    0.50
    ritten
    0.48
    Validated
    0.44
    нки
    0.43
    owanych
    0.43
    𝚎
    0.43
    ້ອຍ
    0.41
    ঠিক
    0.41
    țe
    0.41
    ר
    0.40
    Activations Density 0.006%

    No Known Activations