© 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. 70728
    Prev
    Next
    INDEX
    Explanations

    numbers, lists, and shapes

    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
    ات
    0.54
    body
    0.44
    esa
    0.43
    نائ
    0.43
    ug
    0.42
    ையைப்
    0.42
    体
    0.42
    钰
    0.42
    iros
    0.42
    OMA
    0.42
    POSITIVE LOGITS
     शर्तें
    0.49
    條件
    0.48
     quinze
    0.46
     토
    0.45
     பண
    0.45
     estab
    0.45
     সময়
    0.45
     ENS
    0.44
     умови
    0.44
     土
    0.44
    Activations Density 0.001%

    No Known Activations