© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 70027
    Prev
    Next
    INDEX
    Explanations

    charged or beat down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
     do
    1.34
    unities
    1.22
    ays
    1.21
    incy
    1.21
    obbies
    1.20
    以上に
    1.18
    ferences
    1.17
    佩
    1.15
    enses
    1.15
    を除く
    1.15
    POSITIVE LOGITS
     winger
    1.47
     Sebuah
    1.40
     hydrothermal
    1.37
     Seorang
    1.37
    ("/{
    1.36
     Diamond
    1.33
    Someone
    1.29
    torch
    1.29
    概要
    1.28
     Petrus
    1.28
    Activations Density 0.004%

    No Known Activations