© 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-262K
    7. 125359
    Prev
    Next
    INDEX
    Explanations

    technical and foreign words

    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_262k_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
    ق
    0.59
    ک
    0.51
     (
    0.46
    가
    0.46
    م
    0.45
    /
    0.44
    -
    0.44
    مش
    0.40
    大
    0.40
    WR
    0.40
    POSITIVE LOGITS
     pacientes
    0.49
     rigidbody
    0.46
     Grüße
    0.45
     患者
    0.45
     బి
    0.45
    ành
    0.44
     cutoff
    0.44
     justifyContent
    0.44
     eosin
    0.44
     пациента
    0.44
    Activations Density 0.006%

    No Known Activations