© 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. 77581
    Prev
    Next
    INDEX
    Explanations

    regulating behavior

    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
    鐒
    0.49
     சிதம்ப
    0.46
    ához
    0.46
     Điều
    0.45
     Stateless
    0.44
    нер
    0.44
     массы
    0.44
    펨
    0.44
    ημ
    0.42
    номет
    0.42
    POSITIVE LOGITS
     can
    0.55
    r
    0.53
    pay
    0.50
    ]
    0.49
    し
    0.48
    vette
    0.48
    spectrum
    0.46
     expir
    0.45
    white
    0.45
     teach
    0.44
    Activations Density 0.000%

    No Known Activations