© 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. 2122
    Prev
    Next
    INDEX
    Explanations

    numbers and letters

    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
    案内
    0.32
     GoPro
    0.27
     namam
    0.26
    :";
    0.26
     фильма
    0.25
     സംഭവ
    0.25
    isyen
    0.25
    )="
    0.24
    वत्ता
    0.24
    ᵁ
    0.24
    POSITIVE LOGITS
    Recognition
    0.23
    Bharat
    0.23
     correttamente
    0.22
    حد
    0.22
    стоя
    0.22
     نسم
    0.21
    Coastal
    0.21
    を一
    0.21
     Fo
    0.21
    䪱
    0.21
    Activations Density 0.029%

    No Known Activations