© 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-262K
    4. 108077
    Prev
    Next
    INDEX
    Explanations

    explanation follows sentences

    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
     따
    0.52
     concurred
    0.47
     obligaciones
    0.45
     dernières
    0.45
     últimos
    0.44
     últimas
    0.43
     interacted
    0.43
     রাস
    0.43
     upheld
    0.42
     উত্তরাধিকার
    0.42
    POSITIVE LOGITS
    ة
    0.46
    统一
    0.41
    ێک
    0.41
    AppDesigner
    0.41
     Greens
    0.41
    ھیں
    0.41
    collegiate
    0.40
    proficiency
    0.40
    Korean
    0.40
    ⎆
    0.40
    Activations Density 0.001%

    No Known Activations