© 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-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 386
    Prev
    Next
    INDEX
    Explanations

    sacred ritual and translation

    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_12_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
    ing
    1.56
    的
    1.21
    a
    1.19
    的很
    1.10
    ingin
    1.08
    的具体
    1.06
    ING
    1.05
    aub
    1.05
    를
    1.04
    н
    1.04
    POSITIVE LOGITS
    thaus
    1.41
    zt
    1.27
    ten
    1.24
    stituted
    1.22
    dom
    1.22
    ties
    1.22
    ことが多い
    1.21
    fare
    1.21
    rifice
    1.21
    стов
    1.19
    Activations Density 0.441%

    No Known Activations