© 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. 31-GEMMASCOPE-2-RES-65K
    7. 4705
    Prev
    Next
    INDEX
    Explanations

    material properties and concepts

    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
     Esports
    0.40
    Comp
    0.39
    \
    0.39
    સ
    0.39
     Comp
    0.38
    <mask>
    0.38
    Published
    0.38
    plicated
    0.37
     Language
    0.36
    сным
    0.36
    POSITIVE LOGITS
    အချိန်
    0.47
    擀
    0.43
    waitTime
    0.42
     مدد
    0.41
    some
    0.40
    machine
    0.39
    િક્ષ
    0.39
     SUCCESSFULLY
    0.39
    ਰੇ
    0.39
    ᄈ
    0.39
    Activations Density 0.025%

    No Known Activations