© 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. 2106
    Prev
    Next
    INDEX
    Explanations

    subsequent to qualifying

    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
     రోజు
    0.48
    蒎
    0.47
    债务
    0.46
    肿瘤
    0.43
     отсутствует
    0.43
     コート
    0.43
     отсутствие
    0.42
    扆
    0.41
    ব
    0.40
    riminal
    0.40
    POSITIVE LOGITS
     successivo
    0.53
     ausreiche
    0.48
     qualify
    0.45
     suffis
    0.44
     after
    0.42
     virkelig
    0.42
     تلك
    0.41
     subsequent
    0.41
     fresh
    0.40
     véritable
    0.40
    Activations Density 0.015%

    No Known Activations