© 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. 138686
    Prev
    Next
    INDEX
    Explanations

    SSD and NVMe storage

    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
     visually
    0.54
     salt
    0.49
     collapsed
    0.48
     aproximadamente
    0.46
     por
    0.45
     rim
    0.45
     g
    0.44
     gole
    0.43
     uterine
    0.43
     Ramírez
    0.43
    POSITIVE LOGITS
     낮은
    0.51
    ²',
    0.50
    읽
    0.46
    ASSE
    0.46
    嗪
    0.46
    ITATE
    0.45
    ahanga
    0.45
     सूत्रकृ
    0.45
    전
    0.44
    сыз
    0.43
    Activations Density 0.002%

    No Known Activations