© 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. 40-GEMMASCOPE-2-RES-262K
    7. 223517
    Prev
    Next
    INDEX
    Explanations

    process details

    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_40_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
    TRAVEL
    0.42
    িকো
    0.41
    oddsidemargin
    0.41
    জেল
    0.40
     TRAVEL
    0.40
     reallocation
    0.40
     Wasserstein
    0.40
    匚
    0.40
    paration
    0.39
    ChoiceItemLayout
    0.39
    POSITIVE LOGITS
    ਹੀਂ
    0.36
     markings
    0.35
     dealings
    0.35
     purify
    0.35
     physic
    0.34
    XE
    0.34
    etic
    0.34
     imun
    0.34
    lendi
    0.34
    endy
    0.34
    Activations Density 0.003%

    No Known Activations