© 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. 35972
    Prev
    Next
    INDEX
    Explanations

    more sophisticated qualities

    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
    לה
    0.48
    יה
    0.47
    ﻐ
    0.46
    마
    0.46
    र्में
    0.45
    cual
    0.45
     インド
    0.45
    기
    0.45
     worthless
    0.44
    rizable
    0.44
    POSITIVE LOGITS
     confidently
    0.54
     répond
    0.50
     boldly
    0.44
     establish
    0.43
     McIntyre
    0.42
     Plan
    0.42
     Bud
    0.42
     exemplary
    0.42
     voici
    0.42
    وجوان
    0.42
    Activations Density 0.002%

    No Known Activations