© 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. 101381
    Prev
    Next
    INDEX
    Explanations

    words following numbered or specific tokens

    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
    𝗘
    0.45
     whore
    0.44
    ᱗
    0.44
     shameless
    0.42
    \"");
    0.41
    crever
    0.41
     Godfather
    0.41
     apropri
    0.41
     Pepsi
    0.40
    {[\
    0.40
    POSITIVE LOGITS
    空
    0.48
    Travel
    0.43
    Instruction
    0.41
     ваш
    0.41
    公共
    0.40
    Simulation
    0.40
     insulation
    0.40
    Account
    0.40
     जेल
    0.39
    空中
    0.39
    Activations Density 0.006%

    No Known Activations