© 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. 24563
    Prev
    Next
    INDEX
    Explanations

    positional indicators

    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
     formulation
    0.40
    銜
    0.40
    ohex
    0.39
     حمد
    0.38
     depreciation
    0.38
     resistivity
    0.38
     conhecimentos
    0.36
     Formulation
    0.36
    %$$
    0.36
    L
    0.36
    POSITIVE LOGITS
    ８
    0.47
     ګرځنده
    0.45
    ک
    0.44
    ９
    0.44
    ütü
    0.43
     alış
    0.42
    ట్‌
    0.42
     Over
    0.41
     tế
    0.41
     امیر
    0.41
    Activations Density 0.000%

    No Known Activations