© 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. 139112
    Prev
    Next
    INDEX
    Explanations

    unique selling propositions

    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
     transformations
    0.49
    ல்கள்
    0.47
     disruption
    0.45
    ϵ
    0.45
     строка
    0.45
    耶
    0.45
     mogą
    0.44
     headwinds
    0.44
     anecdotes
    0.43
    ಿಂದ
    0.43
    POSITIVE LOGITS
     Paragu
    0.53
    ikl
    0.48
    鹂
    0.46
     Bacterial
    0.45
    ۜ
    0.44
    äm
    0.43
     الأد
    0.41
     Repert
    0.40
    <0xBE>
    0.40
     Sulfate
    0.40
    Activations Density 0.000%

    No Known Activations