© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128501
    Prev
    Next
    INDEX
    Explanations

    testing boundaries and expressing distress

    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
     Niz
    0.52
    Instruments
    0.46
    بط
    0.44
    اری
    0.44
     Moo
    0.43
     Instruments
    0.43
    ب
    0.42
    با
    0.42
    目标
    0.42
    حضرت
    0.41
    POSITIVE LOGITS
     pourtant
    0.57
     ремо
    0.56
     τῶν
    0.56
     поговори
    0.54
     alertas
    0.54
     preventable
    0.52
     demol
    0.51
     militias
    0.51
     telehealth
    0.50
     potencialmente
    0.50
    Activations Density 0.004%

    No Known Activations