© 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. 16-GEMMASCOPE-2-RES-262K
    7. 626
    Prev
    Next
    INDEX
    Explanations

    delve into

    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_16_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
    的
    0.99
    ні
    0.97
    .
    0.91
    ung
    0.90
    nyt
    0.88
     হৃদয়
    0.88
    3
    0.86
     Belief
    0.86
    2
    0.84
    ди
    0.83
    POSITIVE LOGITS
     innych
    1.09
     ispit
    1.05
     computeEncoder
    1.03
     investimento
    1.02
    ನ
    1.02
     одним
    1.02
     accion
    1.01
     станда
    1.00
     другими
    0.97
     importants
    0.96
    Activations Density 0.030%

    No Known Activations