© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92783
    Prev
    Next
    INDEX
    Explanations

    modelmodel code configuration types

    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
     จึง
    0.44
     प्रवा
    0.43
    彠
    0.42
     त्या
    0.42
     వాటి
    0.42
    этому
    0.41
     ತಮ್ಮ
    0.41
     ดังนั้น
    0.41
     እነ
    0.40
    เท่านั้น
    0.40
    POSITIVE LOGITS
    og
    0.48
    ч
    0.48
    onal
    0.47
    ogast
    0.44
    If
    0.43
    Depending
    0.43
    Alongside
    0.43
     poden
    0.43
     cubed
    0.43
    *
    0.43
    Activations Density 0.002%

    No Known Activations