© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 200087
    Prev
    Next
    INDEX
    Explanations

    type it out

    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_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
     ልዩ
    0.46
     可愛
    0.46
    Adorable
    0.45
    ̱
    0.45
     Để
    0.43
    жеб
    0.43
     戸
    0.43
    
    0.42
    দেশীয়
    0.42
     เลือก
    0.41
    POSITIVE LOGITS
     irgend
    0.43
     pourraient
    0.41
     reduction
    0.40
     autonomously
    0.40
     unterschied
    0.40
     qualcosa
    0.40
     sortie
    0.39
    reduction
    0.39
     agendas
    0.39
     noget
    0.39
    Activations Density 0.006%

    No Known Activations