© 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. 17041
    Prev
    Next
    INDEX
    Explanations

    specific nouns or technical terms

    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
     ਸਮ
    0.45
     displeasure
    0.45
     delight
    0.44
    コレ
    0.43
    風呂
    0.43
     ਪ੍ਰ
    0.43
    सुर
    0.43
    ゲ
    0.43
    ヘ
    0.42
     実
    0.41
    POSITIVE LOGITS
     trainers
    0.45
    作为
    0.44
     anlat
    0.44
     humild
    0.42
     modestly
    0.42
     rằng
    0.41
     unapolog
    0.39
     интервью
    0.39
    独特的
    0.39
    你在
    0.38
    Activations Density 0.010%

    No Known Activations