© 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. 25391
    Prev
    Next
    INDEX
    Explanations

    code snippets and specific entities

    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
     aisément
    0.44
     unequiv
    0.41
    𒅌
    0.40
     当然
    0.37
     informé
    0.37
    腔
    0.36
     expedite
    0.36
     unquestionably
    0.36
    政府采购
    0.36
    যজ্ঞ
    0.36
    POSITIVE LOGITS
     *:
    0.51
    ):
    0.49
    dll
    0.44
     '':
    0.44
     canadian
    0.44
     canada
    0.44
    *:
    0.43
     Calgary
    0.41
     $:
    0.41
     honda
    0.40
    Activations Density 0.002%

    No Known Activations