© 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. 16-GEMMASCOPE-2-RES-262K
    7. 27444
    Prev
    Next
    INDEX
    Explanations

    ally/allyship

    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_16_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
    h
    1.50
    s
    1.41
    z
    1.39
    ية
    1.34
    ين
    1.31
    de
    1.29
    d
    1.29
    c
    1.20
    la
    1.17
    t
    1.17
    POSITIVE LOGITS
    는
    1.54
    える
    1.32
    یک
    1.31
    は
    1.30
    0
    1.24
    ０
    1.21
    ین
    1.10
     лишь
    1.09
    是
    1.02
    𝟬
    1.02
    Activations Density 0.003%

    No Known Activations