© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 15168
    Prev
    Next
    INDEX
    Explanations

    common feeling Uncommon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    🏍
    0.99
     tingkat
    0.95
     cep
    0.94
     caring
    0.93
     *)
    0.93
    রিষ্ঠ
    0.93
    ड्रो
    0.91
    ᕼ
    0.90
    🚁
    0.90
     ceilings
    0.89
    POSITIVE LOGITS
    downarrow
    0.79
    Triangle
    0.78
     Triangle
    0.77
    కర్
    0.77
    Ра
    0.77
    னர்
    0.77
    geht
    0.76
    छाड़
    0.75
    য়ের
    0.74
    Ts
    0.74
    Activations Density 0.000%

    No Known Activations