© 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-65K
    4. 2701
    Prev
    Next
    INDEX
    Explanations

    price, cotton, relative, adjustments

    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_65k_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
    íte
    0.51
    า
    0.48
    关于
    0.45
    ività
    0.43
     Thieves
    0.43
    N
    0.43
    uctive
    0.43
    这
    0.42
    让
    0.42
    𝚣
    0.41
    POSITIVE LOGITS
     මිල
    0.47
    cotton
    0.44
     moglie
    0.44
    messenger
    0.43
     kriter
    0.43
    higher
    0.42
    prices
    0.42
    ɦ
    0.42
     fiyat
    0.41
     buttons
    0.41
    Activations Density 0.001%

    No Known Activations