© 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. 40-GEMMASCOPE-2-RES-262K
    4. 133738
    Prev
    Next
    INDEX
    Explanations

    reading input or scanning files

    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
    🕉
    0.45
     செயல்ப
    0.42
     PHONE
    0.42
     трансформа
    0.41
     WndProc
    0.40
    ዮ
    0.40
     আবরণ
    0.39
    ವರಿಗೆ
    0.38
     також
    0.38
     adimensional
    0.38
    POSITIVE LOGITS
    InRange
    0.42
     peach
    0.42
    溉
    0.40
    Lex
    0.38
     packers
    0.37
    來越
    0.37
     Peach
    0.36
    悦
    0.36
    ophil
    0.36
     পেল
    0.35
    Activations Density 0.002%

    No Known Activations