© 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. 36760
    Prev
    Next
    INDEX
    Explanations

    places and travel experiences

    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
    ette
    0.53
    s
    0.52
    ady
    0.50
    ook
    0.47
    ational
    0.45
    ets
    0.45
    ethy
    0.44
    \
    0.44
    ula
    0.44
     maladies
    0.43
    POSITIVE LOGITS
    くれます
    0.47
    キャンプ
    0.42
    ској
    0.42
    ネタ
    0.40
    釭
    0.40
    不在
    0.39
    كن
    0.39
    زي
    0.39
    nicht
    0.39
    цвет
    0.38
    Activations Density 0.016%

    No Known Activations