© 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. 28288
    Prev
    Next
    INDEX
    Explanations

    Generate Multiple

    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
    "
    0.44
    Е
    0.44
    Ц
    0.42
    Ро
    0.41
    “
    0.40
    Бу
    0.40
    да
    0.40
    Т
    0.39
    /**
    0.39
    Гу
    0.39
    POSITIVE LOGITS
     سلي
    0.49
     සම්
    0.45
    の種類
    0.43
     المنطقة
    0.43
     cuyos
    0.42
     علماء
    0.42
    庸
    0.41
     روح
    0.40
     అన్ని
    0.40
     με
    0.40
    Activations Density 0.005%

    No Known Activations